From 595a66b8361d6a240aafa6bb4450f0133b6a7a96 Mon Sep 17 00:00:00 2001
From: Shagun Sodhani <sshagunsodhani@gmail.com>
Date: Sun, 12 Feb 2023 13:52:02 -0500
Subject: [PATCH] Add toolformer paper

---
 404.html                                      |   2 +-
 ...-Model-for-Natural-Language-Inference.html |   8 +-
 ...pendency-Parser-using-Neural-Networks.html |   8 +-
 A-Foliated-View-of-Transfer-Learning.html     |   8 +-
 ...Deep-Learning-with-Symbolic-Knowledge.html |   8 +-
 ...-Learning-of-Language-Representations.html |   8 +-
 Abductive-Commonsense-Reasoning.html          |   8 +-
 ...batch-SGD-Training-ImageNet-in-1-Hour.html |   8 +-
 ...k-Prediction-a-View-from-the-Trenches.html |   8 +-
 ...-with-Composition-in-Classifier-Space.html |   8 +-
 ...ing-in-Gradient-Based-Neural-Networks.html |   8 +-
 ...en-Representations-and-Task-Semantics.html |   8 +-
 ...works-for-Natural-Language-Processing.html |   8 +-
 ...zation-in-Deep-Reinforcement-Learning.html |   8 +-
 ...ider-Optima-and-Better-Generalization.html |   8 +-
 ...age-Learning-With-a-Human-In-the-Loop.html |   8 +-
 Born-Again-Neural-Networks.html               |   8 +-
 ...ears-later-How-the-rules-have-changed.html |   8 +-
 ...sentations-for-Reinforcement-Learning.html |   8 +-
 ...centralized-structured-storage-system.html |   8 +-
 ...of-Independent-Deep-Generative-Models.html |   8 +-
 Compositional-Explanations-of-Neurons.html    |   8 +-
 Conditional-Similarity-Networks.html          |   8 +-
 ...rn-Distributed-Database-System-Design.html |   8 +-
 Continual-learning-with-hypernetworks.html    |   8 +-
 ...e-Learning-of-Structured-World-Models.html |   8 +-
 ...ng-Rates-for-Training-Neural-Networks.html |   8 +-
 ...ent-for-Internet-Scale-Single-Sign-On.html |   8 +-
 ...aking-via-Local-Economic-Transactions.html |   8 +-
 ...-Networks-for-YouTube-Recommendations.html |   8 +-
 ...rcement-Learning-and-the-Deadly-Triad.html |   8 +-
 ...s-using-Probabilistic-Dynamics-Models.html |   8 +-
 ...r-container-based-distributed-systems.html |   8 +-
 ...ing-the-Knowledge-in-a-Neural-Network.html |   8 +-
 ...ning-Skills-without-a-Reward-Function.html |   8 +-
 ...Discriminators-Rather-Than-Generators.html |   8 +-
 Efficient-Lifelong-Learning-with-A-GEM.html   |   8 +-
 ...l-Language-in-Multi-Agent-Populations.html |   8 +-
 ...ion-with-Internal-and-External-Memory.html |   8 +-
 ...y-based-Models-for-Continual-Learning.html |   8 +-
 ...Purpose-of-Actions-in-Procedural-Text.html |   8 +-
 ...and-Data-for-Image-Question-Answering.html |   8 +-
 ...imple-Siamese-Representation-Learning.html |   8 +-
 ...nforcement-Learning-from-Observations.html |   8 +-
 ...-Explanation-of-Graph-Neural-Networks.html |   8 +-
 ...with-Micro-Batch-Pipeline-Parallelism.html |   8 +-
 ...ation-with-Pointer-Generator-Networks.html |   8 +-
 ...nough-Compositional-Data-Augmentation.html |   8 +-
 ...tor-Learner-Architectures-for-Deep-RL.html |   8 +-
 ...-Balancing-in-Deep-Multitask-Networks.html |   8 +-
 Gradient-Surgery-for-Multi-Task-Learning.html |   8 +-
 ...lection-for-online-continual-learning.html |   8 +-
 ...-Representation-Learning-for-Networks.html |   8 +-
 Hamiltonian-Neural-Networks.html              |   8 +-
 ...-Yield,-and-Scalable-Tolerant-Systems.html |   8 +-
 ...-Learning-with-Differentiable-Pooling.html |   8 +-
 ...e-of-Proprioceptive-Periodic-Policies.html |   8 +-
 ...rder-organization-of-complex-networks.html |   8 +-
 Hindsight-Experience-Replay.html              |   8 +-
 HoME-a-Household-Multimodal-Environment.html  |   8 +-
 How-to-train-your-MAML.html                   |   8 +-
 ...-are-features-in-deep-neural-networks.html |   8 +-
 HyperNetworks.html                            |   8 +-
 ...gents-for-Deep-Reinforcement-Learning.html |   8 +-
 ...-Evidence-with-Reinforcement-Learning.html |   8 +-
 Kronecker-Recurrent-Units.html                |   8 +-
 Large-Memory-Layers-with-Product-Keys.html    |   8 +-
 ...-Optimizers-that-Scale-and-Generalize.html |   8 +-
 ...ng-Explanations-That-Are-Hard-To-Vary.html |   8 +-
 Learning-Independent-Causal-Mechanisms.html   |   8 +-
 ...AT-Solver-from-Single-Bit-Supervision.html |   8 +-
 ...to-Compute-Word-Embeddings-On-the-Fly.html |   8 +-
 ...-Images-for-Visual-Question-Answering.html |   8 +-
 ...-Memory-for-Recurrent-Neural-Networks.html |   8 +-
 ...cene-Decomposition-and-Representation.html |   8 +-
 ...standing-in-Visual-Question-Answering.html |   8 +-
 ...n-in-the-Wild-Findings-and-Challenges.html |   8 +-
 ...hogi-by-Planning-with-a-Learned-Model.html |   8 +-
 ...Abstract-Reasoning-in-Neural-Networks.html |   8 +-
 Memory-Based-Parameter-Adaption.html          |   8 +-
 ...-Unsupervised-Representation-Learning.html |   8 +-
 ...-of-Structured-Exploration-Strategies.html |   8 +-
 ...hical-Lifelong-Reinforcement-Learning.html |   8 +-
 Modular-meta-learning.html                    |   8 +-
 ...le-Model-Based-Reinforcement-Learning.html |   8 +-
 ...ating-Learning-via-Knowledge-Transfer.html |   8 +-
 ...e-Building-Blocks-of-Complex-Networks.html |   8 +-
 ...zation-in-Deep-Reinforcement-Learning.html |   8 +-
 ...Message-Passing-for-Quantum-Chemistry.html |   8 +-
 Neural-Module-Networks.html                   |   8 +-
 ...nal-Inference-for-Interacting-Systems.html |   8 +-
 ...Overfitting-in-Reinforcement-Learning.html |   8 +-
 ...Warm-Starting-Neural-Network-Training.html |   8 +-
 One-Model-To-Learn-Them-All.html              |   8 +-
 ...xtrapolation-via-Structured-MaxEnt-RL.html |   8 +-
 ...with-Memory-Augmented-Neural-Networks.html |   8 +-
 ...arsely-Gated-Mixture-of-Experts-Layer.html |   8 +-
 ...-New-Benchmark-for-Physical-Reasoning.html |   8 +-
 ...rge-scale-Heterogeneous-Text-Networks.html |   8 +-
 ...Learning-Hierarchical-Representations.html |   8 +-
 Pointer-Networks.html                         |   8 +-
 ...-Predicting-Clicks-on-Ads-at-Facebook.html |   8 +-
 ...ng-Graph-Neural-Networks-with-Kernels.html |   8 +-
 ...tribution-Examples-in-Neural-Networks.html |   8 +-
 ...eralization-in-Reinforcement-Learning.html |   8 +-
 ...rehension-with-Self-matching-Networks.html |   8 +-
 ...derstanding-the-Effectiveness-of-MAML.html |   8 +-
 ...pedia-to-Answer-Open-Domain-Questions.html |   8 +-
 ...Stop-Reading-in-Machine-Comprehension.html |   8 +-
 ...tworks-for-Neural-Machine-Translation.html |   8 +-
 Relational-Reinforcement-Learning.html        |   8 +-
 ...ations-Reduce-Catastrophic-Forgetting.html |   8 +-
 ...n-Tradeoffs-for-Hyperbolic-Embeddings.html |   8 +-
 ...ing-Fundamentals-of-Experience-Replay.html |   8 +-
 ...rvised-Learning-with-Graph-Embeddings.html |   8 +-
 ...ces-Managing-Technical-Debt-at-Google.html |   8 +-
 ...Permutation-Invariant-Neural-Networks.html |   8 +-
 ...aseline-for-Visual-Question-Answering.html |   8 +-
 ...nctions-for-Deep-Top-k-Classification.html |   8 +-
 StarSpace-Embed-All-The-Things.html           |   8 +-
 ...stems-Using-Recurrent-Neural-Networks.html |   8 +-
 Superposition-of-many-models-into-one.html    |   8 +-
 Supervised-Contrastive-Learning.html          |   8 +-
 Swish-A-self-gated-activation-function.html   |   8 +-
 ...ptation-across-Tasks-and-Environments.html |   8 +-
 ...Batch-Normalization-for-Meta-Learning.html |   8 +-
 ...rmulation-with-Reinforcement-Learning.html |   8 +-
 ...hesis-Training-Pruned-Neural-Networks.html |   8 +-
 The-Tail-at-Scale.html                        |   8 +-
 ...ined-Representations-to-Diverse-Tasks.html |   8 +-
 ...els-Can-Teach-Themselves-to-Use-Tools.html | 488 ++++++++++++++++++
 ...-Theory-of-State-Abstraction-for-MDPs.html |   8 +-
 ...ural-benchmark-for-continual-learning.html |   8 +-
 ...zation-for-Knowledge-Graph-Completion.html |   8 +-
 ...fer-Learning-in-Machine-Comprehension.html |   8 +-
 ...tions-of-Word2Vec-for-Syntax-Problems.html |   8 +-
 ...pervised-Learning-By-Predicting-Noise.html |   8 +-
 VQA-Visual-Question-Answering.html            |   8 +-
 ...-Than-10,000-Image-Categories-Tell-Us.html |   8 +-
 When-Do-Curricula-Work.html                   |   8 +-
 ...ent-Models-Don-t-Need-To-Be-Recurrent.html |   8 +-
 ...tric-models-in-reinforcement-learning.html |   8 +-
 ...epresentations-via-Gaussian-Embedding.html |   8 +-
 ...del,-and-You-Should-Treat-it-Like-One.html |   8 +-
 ...-by-Generating-Task-specific-Adapters.html |   8 +-
 archieve.html                                 |   4 +-
 atom.xml                                      | 230 ++++++---
 index.html                                    |  14 +-
 mixup-Beyond-Empirical-Risk-Minimization.html |   8 +-
 page10/index.html                             |   2 +-
 page11/index.html                             |   2 +-
 page12/index.html                             |   2 +-
 page13/index.html                             |   2 +-
 page14/index.html                             |   2 +-
 page15/index.html                             |   2 +-
 page2/index.html                              |   2 +-
 page3/index.html                              |   2 +-
 page4/index.html                              |   2 +-
 page5/index.html                              |   2 +-
 page6/index.html                              |   2 +-
 page7/index.html                              |   2 +-
 page8/index.html                              |   2 +-
 page9/index.html                              |   2 +-
 tags.html                                     | 104 ++--
 164 files changed, 1323 insertions(+), 699 deletions(-)
 create mode 100644 Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools.html

diff --git a/404.html b/404.html
index 6792b7a4..f77559d0 100644
--- a/404.html
+++ b/404.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/A-Decomposable-Attention-Model-for-Natural-Language-Inference.html b/A-Decomposable-Attention-Model-for-Natural-Language-Inference.html
index d75cff45..11a7fd4c 100644
--- a/A-Decomposable-Attention-Model-for-Natural-Language-Inference.html
+++ b/A-Decomposable-Attention-Model-for-Natural-Language-Inference.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -257,9 +257,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/A-Fast-and-Accurate-Dependency-Parser-using-Neural-Networks.html b/A-Fast-and-Accurate-Dependency-Parser-using-Neural-Networks.html
index 22f999ed..4eed5b47 100644
--- a/A-Fast-and-Accurate-Dependency-Parser-using-Neural-Networks.html
+++ b/A-Fast-and-Accurate-Dependency-Parser-using-Neural-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -258,9 +258,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/A-Foliated-View-of-Transfer-Learning.html b/A-Foliated-View-of-Transfer-Learning.html
index 881c62d4..1d2e2cef 100644
--- a/A-Foliated-View-of-Transfer-Learning.html
+++ b/A-Foliated-View-of-Transfer-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -263,9 +263,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/A-Semantic-Loss-Function-for-Deep-Learning-with-Symbolic-Knowledge.html b/A-Semantic-Loss-Function-for-Deep-Learning-with-Symbolic-Knowledge.html
index 4927c339..e3d58dd9 100644
--- a/A-Semantic-Loss-Function-for-Deep-Learning-with-Symbolic-Knowledge.html
+++ b/A-Semantic-Loss-Function-for-Deep-Learning-with-Symbolic-Knowledge.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -346,9 +346,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/ALBERT-A-Lite-BERT-for-Self-supervised-Learning-of-Language-Representations.html b/ALBERT-A-Lite-BERT-for-Self-supervised-Learning-of-Language-Representations.html
index b25a1d27..41aa63de 100644
--- a/ALBERT-A-Lite-BERT-for-Self-supervised-Learning-of-Language-Representations.html
+++ b/ALBERT-A-Lite-BERT-for-Self-supervised-Learning-of-Language-Representations.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -305,9 +305,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Abductive-Commonsense-Reasoning.html b/Abductive-Commonsense-Reasoning.html
index 7533e81e..377e7e48 100644
--- a/Abductive-Commonsense-Reasoning.html
+++ b/Abductive-Commonsense-Reasoning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -271,9 +271,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Accurate-Large-Minibatch-SGD-Training-ImageNet-in-1-Hour.html b/Accurate-Large-Minibatch-SGD-Training-ImageNet-in-1-Hour.html
index 14cb61c9..ff402f9e 100644
--- a/Accurate-Large-Minibatch-SGD-Training-ImageNet-in-1-Hour.html
+++ b/Accurate-Large-Minibatch-SGD-Training-ImageNet-in-1-Hour.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -298,9 +298,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Ad-Click-Prediction-a-View-from-the-Trenches.html b/Ad-Click-Prediction-a-View-from-the-Trenches.html
index 79404e4d..cf593ccc 100644
--- a/Ad-Click-Prediction-a-View-from-the-Trenches.html
+++ b/Ad-Click-Prediction-a-View-from-the-Trenches.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -335,9 +335,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Alpha-Net-Adaptation-with-Composition-in-Classifier-Space.html b/Alpha-Net-Adaptation-with-Composition-in-Classifier-Space.html
index 4ac23e50..7b69d40c 100644
--- a/Alpha-Net-Adaptation-with-Composition-in-Classifier-Space.html
+++ b/Alpha-Net-Adaptation-with-Composition-in-Classifier-Space.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -279,9 +279,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/An-Empirical-Investigation-of-Catastrophic-Forgetting-in-Gradient-Based-Neural-Networks.html b/An-Empirical-Investigation-of-Catastrophic-Forgetting-in-Gradient-Based-Neural-Networks.html
index 6882f090..dd9c8e6a 100644
--- a/An-Empirical-Investigation-of-Catastrophic-Forgetting-in-Gradient-Based-Neural-Networks.html
+++ b/An-Empirical-Investigation-of-Catastrophic-Forgetting-in-Gradient-Based-Neural-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -271,9 +271,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Anatomy-of-Catastrophic-Forgetting-Hidden-Representations-and-Task-Semantics.html b/Anatomy-of-Catastrophic-Forgetting-Hidden-Representations-and-Task-Semantics.html
index 9ae79da2..ab395376 100644
--- a/Anatomy-of-Catastrophic-Forgetting-Hidden-Representations-and-Task-Semantics.html
+++ b/Anatomy-of-Catastrophic-Forgetting-Hidden-Representations-and-Task-Semantics.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -373,9 +373,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Ask-Me-Anything-Dynamic-Memory-Networks-for-Natural-Language-Processing.html b/Ask-Me-Anything-Dynamic-Memory-Networks-for-Natural-Language-Processing.html
index 85190311..08b2c9b0 100644
--- a/Ask-Me-Anything-Dynamic-Memory-Networks-for-Natural-Language-Processing.html
+++ b/Ask-Me-Anything-Dynamic-Memory-Networks-for-Natural-Language-Processing.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -344,9 +344,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Assessing-Generalization-in-Deep-Reinforcement-Learning.html b/Assessing-Generalization-in-Deep-Reinforcement-Learning.html
index 85d2f745..7c82930a 100644
--- a/Assessing-Generalization-in-Deep-Reinforcement-Learning.html
+++ b/Assessing-Generalization-in-Deep-Reinforcement-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -332,9 +332,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Averaging-Weights-leads-to-Wider-Optima-and-Better-Generalization.html b/Averaging-Weights-leads-to-Wider-Optima-and-Better-Generalization.html
index 76aa3330..585f7403 100644
--- a/Averaging-Weights-leads-to-Wider-Optima-and-Better-Generalization.html
+++ b/Averaging-Weights-leads-to-Wider-Optima-and-Better-Generalization.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -282,9 +282,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/BabyAI-First-Steps-Towards-Grounded-Language-Learning-With-a-Human-In-the-Loop.html b/BabyAI-First-Steps-Towards-Grounded-Language-Learning-With-a-Human-In-the-Loop.html
index 28c23ce4..9566e083 100644
--- a/BabyAI-First-Steps-Towards-Grounded-Language-Learning-With-a-Human-In-the-Loop.html
+++ b/BabyAI-First-Steps-Towards-Grounded-Language-Learning-With-a-Human-In-the-Loop.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -345,9 +345,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Born-Again-Neural-Networks.html b/Born-Again-Neural-Networks.html
index 5f0cfb3b..e0c4a5da 100644
--- a/Born-Again-Neural-Networks.html
+++ b/Born-Again-Neural-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -314,9 +314,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/CAP-twelve-years-later-How-the-rules-have-changed.html b/CAP-twelve-years-later-How-the-rules-have-changed.html
index ba3deb85..0e818ecf 100644
--- a/CAP-twelve-years-later-How-the-rules-have-changed.html
+++ b/CAP-twelve-years-later-How-the-rules-have-changed.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -345,9 +345,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/CURL-Contrastive-Unsupervised-Representations-for-Reinforcement-Learning.html b/CURL-Contrastive-Unsupervised-Representations-for-Reinforcement-Learning.html
index 974c262e..1965470c 100644
--- a/CURL-Contrastive-Unsupervised-Representations-for-Reinforcement-Learning.html
+++ b/CURL-Contrastive-Unsupervised-Representations-for-Reinforcement-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -307,9 +307,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Cassandra-a-decentralized-structured-storage-system.html b/Cassandra-a-decentralized-structured-storage-system.html
index 071e3591..6b15b46e 100644
--- a/Cassandra-a-decentralized-structured-storage-system.html
+++ b/Cassandra-a-decentralized-structured-storage-system.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -292,9 +292,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Competitive-Training-of-Mixtures-of-Independent-Deep-Generative-Models.html b/Competitive-Training-of-Mixtures-of-Independent-Deep-Generative-Models.html
index 889b9122..98ce4822 100644
--- a/Competitive-Training-of-Mixtures-of-Independent-Deep-Generative-Models.html
+++ b/Competitive-Training-of-Mixtures-of-Independent-Deep-Generative-Models.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -286,9 +286,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Compositional-Explanations-of-Neurons.html b/Compositional-Explanations-of-Neurons.html
index cdf7741e..cd0a364c 100644
--- a/Compositional-Explanations-of-Neurons.html
+++ b/Compositional-Explanations-of-Neurons.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -346,9 +346,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Conditional-Similarity-Networks.html b/Conditional-Similarity-Networks.html
index e73030ea..840f45b1 100644
--- a/Conditional-Similarity-Networks.html
+++ b/Conditional-Similarity-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -294,9 +294,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Consistency-Tradeoffs-in-Modern-Distributed-Database-System-Design.html b/Consistency-Tradeoffs-in-Modern-Distributed-Database-System-Design.html
index cc07f959..957dc129 100644
--- a/Consistency-Tradeoffs-in-Modern-Distributed-Database-System-Design.html
+++ b/Consistency-Tradeoffs-in-Modern-Distributed-Database-System-Design.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -314,9 +314,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Continual-learning-with-hypernetworks.html b/Continual-learning-with-hypernetworks.html
index 4f1f081d..4f61c15c 100644
--- a/Continual-learning-with-hypernetworks.html
+++ b/Continual-learning-with-hypernetworks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -311,9 +311,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Contrastive-Learning-of-Structured-World-Models.html b/Contrastive-Learning-of-Structured-World-Models.html
index 3ee06647..6e6062a4 100644
--- a/Contrastive-Learning-of-Structured-World-Models.html
+++ b/Contrastive-Learning-of-Structured-World-Models.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -322,9 +322,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Cyclical-Learning-Rates-for-Training-Neural-Networks.html b/Cyclical-Learning-Rates-for-Training-Neural-Networks.html
index 18ae4cde..6bf6d1dc 100644
--- a/Cyclical-Learning-Rates-for-Training-Neural-Networks.html
+++ b/Cyclical-Learning-Rates-for-Training-Neural-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -257,9 +257,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Data-Management-for-Internet-Scale-Single-Sign-On.html b/Data-Management-for-Internet-Scale-Single-Sign-On.html
index 168790d1..5b06660a 100644
--- a/Data-Management-for-Internet-Scale-Single-Sign-On.html
+++ b/Data-Management-for-Internet-Scale-Single-Sign-On.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -318,9 +318,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Decentralized-Reinforcement-Learning-Global-Decision-Making-via-Local-Economic-Transactions.html b/Decentralized-Reinforcement-Learning-Global-Decision-Making-via-Local-Economic-Transactions.html
index 4aea4669..bb92f318 100644
--- a/Decentralized-Reinforcement-Learning-Global-Decision-Making-via-Local-Economic-Transactions.html
+++ b/Decentralized-Reinforcement-Learning-Global-Decision-Making-via-Local-Economic-Transactions.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -325,9 +325,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Deep-Neural-Networks-for-YouTube-Recommendations.html b/Deep-Neural-Networks-for-YouTube-Recommendations.html
index ba2d4a61..c1eeebf7 100644
--- a/Deep-Neural-Networks-for-YouTube-Recommendations.html
+++ b/Deep-Neural-Networks-for-YouTube-Recommendations.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -342,9 +342,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Deep-Reinforcement-Learning-and-the-Deadly-Triad.html b/Deep-Reinforcement-Learning-and-the-Deadly-Triad.html
index 1cb3118e..c558f390 100644
--- a/Deep-Reinforcement-Learning-and-the-Deadly-Triad.html
+++ b/Deep-Reinforcement-Learning-and-the-Deadly-Triad.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -330,9 +330,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Deep-Reinforcement-Learning-in-a-Handful-of-Trials-using-Probabilistic-Dynamics-Models.html b/Deep-Reinforcement-Learning-in-a-Handful-of-Trials-using-Probabilistic-Dynamics-Models.html
index 68f1ec7f..3a4cd5db 100644
--- a/Deep-Reinforcement-Learning-in-a-Handful-of-Trials-using-Probabilistic-Dynamics-Models.html
+++ b/Deep-Reinforcement-Learning-in-a-Handful-of-Trials-using-Probabilistic-Dynamics-Models.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -272,9 +272,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Design-patterns-for-container-based-distributed-systems.html b/Design-patterns-for-container-based-distributed-systems.html
index 9fb46b62..7f904ec5 100644
--- a/Design-patterns-for-container-based-distributed-systems.html
+++ b/Design-patterns-for-container-based-distributed-systems.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -259,9 +259,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Distilling-the-Knowledge-in-a-Neural-Network.html b/Distilling-the-Knowledge-in-a-Neural-Network.html
index 2343a55d..2cdcaee3 100644
--- a/Distilling-the-Knowledge-in-a-Neural-Network.html
+++ b/Distilling-the-Knowledge-in-a-Neural-Network.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -283,9 +283,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Diversity-is-All-You-Need-Learning-Skills-without-a-Reward-Function.html b/Diversity-is-All-You-Need-Learning-Skills-without-a-Reward-Function.html
index 97c729fa..29b76d0a 100644
--- a/Diversity-is-All-You-Need-Learning-Skills-without-a-Reward-Function.html
+++ b/Diversity-is-All-You-Need-Learning-Skills-without-a-Reward-Function.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -295,9 +295,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/ELECTRA-Pre-training-Text-Encoders-as-Discriminators-Rather-Than-Generators.html b/ELECTRA-Pre-training-Text-Encoders-as-Discriminators-Rather-Than-Generators.html
index aa61c975..0e008087 100644
--- a/ELECTRA-Pre-training-Text-Encoders-as-Discriminators-Rather-Than-Generators.html
+++ b/ELECTRA-Pre-training-Text-Encoders-as-Discriminators-Rather-Than-Generators.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -341,9 +341,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Efficient-Lifelong-Learning-with-A-GEM.html b/Efficient-Lifelong-Learning-with-A-GEM.html
index 7349298a..2a6b3cde 100644
--- a/Efficient-Lifelong-Learning-with-A-GEM.html
+++ b/Efficient-Lifelong-Learning-with-A-GEM.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -355,9 +355,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Emergence-of-Grounded-Compositional-Language-in-Multi-Agent-Populations.html b/Emergence-of-Grounded-Compositional-Language-in-Multi-Agent-Populations.html
index 31d69b23..f5cf560c 100644
--- a/Emergence-of-Grounded-Compositional-Language-in-Multi-Agent-Populations.html
+++ b/Emergence-of-Grounded-Compositional-Language-in-Multi-Agent-Populations.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -312,9 +312,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Emotional-Chatting-Machine-Emotional-Conversation-Generation-with-Internal-and-External-Memory.html b/Emotional-Chatting-Machine-Emotional-Conversation-Generation-with-Internal-and-External-Memory.html
index 060b4e25..eade4822 100644
--- a/Emotional-Chatting-Machine-Emotional-Conversation-Generation-with-Internal-and-External-Memory.html
+++ b/Emotional-Chatting-Machine-Emotional-Conversation-Generation-with-Internal-and-External-Memory.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -270,9 +270,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Energy-based-Models-for-Continual-Learning.html b/Energy-based-Models-for-Continual-Learning.html
index 006120c6..5c6ad697 100644
--- a/Energy-based-Models-for-Continual-Learning.html
+++ b/Energy-based-Models-for-Continual-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -325,9 +325,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Everything-Happens-for-a-Reason-Discovering-the-Purpose-of-Actions-in-Procedural-Text.html b/Everything-Happens-for-a-Reason-Discovering-the-Purpose-of-Actions-in-Procedural-Text.html
index 48a40941..fa8dd5aa 100644
--- a/Everything-Happens-for-a-Reason-Discovering-the-Purpose-of-Actions-in-Procedural-Text.html
+++ b/Everything-Happens-for-a-Reason-Discovering-the-Purpose-of-Actions-in-Procedural-Text.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -395,9 +395,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Exploring-Models-and-Data-for-Image-Question-Answering.html b/Exploring-Models-and-Data-for-Image-Question-Answering.html
index 8b5c4475..e09e36aa 100644
--- a/Exploring-Models-and-Data-for-Image-Question-Answering.html
+++ b/Exploring-Models-and-Data-for-Image-Question-Answering.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -268,9 +268,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Exploring-Simple-Siamese-Representation-Learning.html b/Exploring-Simple-Siamese-Representation-Learning.html
index e2208fb3..9b88e3da 100644
--- a/Exploring-Simple-Siamese-Representation-Learning.html
+++ b/Exploring-Simple-Siamese-Representation-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -298,9 +298,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Extrapolating-Beyond-Suboptimal-Demonstrations-via-Inverse-Reinforcement-Learning-from-Observations.html b/Extrapolating-Beyond-Suboptimal-Demonstrations-via-Inverse-Reinforcement-Learning-from-Observations.html
index 0ca2f46b..672cb18b 100644
--- a/Extrapolating-Beyond-Suboptimal-Demonstrations-via-Inverse-Reinforcement-Learning-from-Observations.html
+++ b/Extrapolating-Beyond-Suboptimal-Demonstrations-via-Inverse-Reinforcement-Learning-from-Observations.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -263,9 +263,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/GNN-Explainer-A-Tool-for-Post-hoc-Explanation-of-Graph-Neural-Networks.html b/GNN-Explainer-A-Tool-for-Post-hoc-Explanation-of-Graph-Neural-Networks.html
index 07a05217..2adc462e 100644
--- a/GNN-Explainer-A-Tool-for-Post-hoc-Explanation-of-Graph-Neural-Networks.html
+++ b/GNN-Explainer-A-Tool-for-Post-hoc-Explanation-of-Graph-Neural-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -391,9 +391,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/GPipe-Easy-Scaling-with-Micro-Batch-Pipeline-Parallelism.html b/GPipe-Easy-Scaling-with-Micro-Batch-Pipeline-Parallelism.html
index 46e57acf..11678bb8 100644
--- a/GPipe-Easy-Scaling-with-Micro-Batch-Pipeline-Parallelism.html
+++ b/GPipe-Easy-Scaling-with-Micro-Batch-Pipeline-Parallelism.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -261,9 +261,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Get-To-The-Point-Summarization-with-Pointer-Generator-Networks.html b/Get-To-The-Point-Summarization-with-Pointer-Generator-Networks.html
index 311254f4..89c5d0b0 100644
--- a/Get-To-The-Point-Summarization-with-Pointer-Generator-Networks.html
+++ b/Get-To-The-Point-Summarization-with-Pointer-Generator-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -263,9 +263,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Good-Enough-Compositional-Data-Augmentation.html b/Good-Enough-Compositional-Data-Augmentation.html
index 8ae5a970..190193e7 100644
--- a/Good-Enough-Compositional-Data-Augmentation.html
+++ b/Good-Enough-Compositional-Data-Augmentation.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -238,9 +238,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Gossip-based-Actor-Learner-Architectures-for-Deep-RL.html b/Gossip-based-Actor-Learner-Architectures-for-Deep-RL.html
index 7bfc2c12..21acd720 100644
--- a/Gossip-based-Actor-Learner-Architectures-for-Deep-RL.html
+++ b/Gossip-based-Actor-Learner-Architectures-for-Deep-RL.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -253,9 +253,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/GradNorm-Gradient-Normalization-for-Adaptive-Loss-Balancing-in-Deep-Multitask-Networks.html b/GradNorm-Gradient-Normalization-for-Adaptive-Loss-Balancing-in-Deep-Multitask-Networks.html
index fdc13f41..2b5a3dff 100644
--- a/GradNorm-Gradient-Normalization-for-Adaptive-Loss-Balancing-in-Deep-Multitask-Networks.html
+++ b/GradNorm-Gradient-Normalization-for-Adaptive-Loss-Balancing-in-Deep-Multitask-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -290,9 +290,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Gradient-Surgery-for-Multi-Task-Learning.html b/Gradient-Surgery-for-Multi-Task-Learning.html
index dd7046b6..0e562cca 100644
--- a/Gradient-Surgery-for-Multi-Task-Learning.html
+++ b/Gradient-Surgery-for-Multi-Task-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -304,9 +304,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Gradient-based-sample-selection-for-online-continual-learning.html b/Gradient-based-sample-selection-for-online-continual-learning.html
index 25c92bbf..61ed5113 100644
--- a/Gradient-based-sample-selection-for-online-continual-learning.html
+++ b/Gradient-based-sample-selection-for-online-continual-learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -313,9 +313,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/HARP-Hierarchical-Representation-Learning-for-Networks.html b/HARP-Hierarchical-Representation-Learning-for-Networks.html
index e49e3f73..9d069f58 100644
--- a/HARP-Hierarchical-Representation-Learning-for-Networks.html
+++ b/HARP-Hierarchical-Representation-Learning-for-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -246,9 +246,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Hamiltonian-Neural-Networks.html b/Hamiltonian-Neural-Networks.html
index a9aac38f..d70c8213 100644
--- a/Hamiltonian-Neural-Networks.html
+++ b/Hamiltonian-Neural-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -270,9 +270,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Harvest,-Yield,-and-Scalable-Tolerant-Systems.html b/Harvest,-Yield,-and-Scalable-Tolerant-Systems.html
index 17715a66..6687739c 100644
--- a/Harvest,-Yield,-and-Scalable-Tolerant-Systems.html
+++ b/Harvest,-Yield,-and-Scalable-Tolerant-Systems.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -273,9 +273,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Hierarchical-Graph-Representation-Learning-with-Differentiable-Pooling.html b/Hierarchical-Graph-Representation-Learning-with-Differentiable-Pooling.html
index 5db47cff..1df7e780 100644
--- a/Hierarchical-Graph-Representation-Learning-with-Differentiable-Pooling.html
+++ b/Hierarchical-Graph-Representation-Learning-with-Differentiable-Pooling.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -324,9 +324,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Hierarchical-RL-Using-an-Ensemble-of-Proprioceptive-Periodic-Policies.html b/Hierarchical-RL-Using-an-Ensemble-of-Proprioceptive-Periodic-Policies.html
index f93544cf..041e59ad 100644
--- a/Hierarchical-RL-Using-an-Ensemble-of-Proprioceptive-Periodic-Policies.html
+++ b/Hierarchical-RL-Using-an-Ensemble-of-Proprioceptive-Periodic-Policies.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -298,9 +298,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Higher-order-organization-of-complex-networks.html b/Higher-order-organization-of-complex-networks.html
index b4e0bfdc..4bbccb5c 100644
--- a/Higher-order-organization-of-complex-networks.html
+++ b/Higher-order-organization-of-complex-networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -253,9 +253,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Hindsight-Experience-Replay.html b/Hindsight-Experience-Replay.html
index 5560fbcf..791dfa6a 100644
--- a/Hindsight-Experience-Replay.html
+++ b/Hindsight-Experience-Replay.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -267,9 +267,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/HoME-a-Household-Multimodal-Environment.html b/HoME-a-Household-Multimodal-Environment.html
index b588499f..b94f3fda 100644
--- a/HoME-a-Household-Multimodal-Environment.html
+++ b/HoME-a-Household-Multimodal-Environment.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -294,9 +294,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/How-to-train-your-MAML.html b/How-to-train-your-MAML.html
index a4ddbd65..c92654d9 100644
--- a/How-to-train-your-MAML.html
+++ b/How-to-train-your-MAML.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -282,9 +282,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/How-transferable-are-features-in-deep-neural-networks.html b/How-transferable-are-features-in-deep-neural-networks.html
index afd291e6..d56bf76d 100644
--- a/How-transferable-are-features-in-deep-neural-networks.html
+++ b/How-transferable-are-features-in-deep-neural-networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -290,9 +290,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/HyperNetworks.html b/HyperNetworks.html
index bf7fc70a..362d2a64 100644
--- a/HyperNetworks.html
+++ b/HyperNetworks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -274,9 +274,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Imagination-Augmented-Agents-for-Deep-Reinforcement-Learning.html b/Imagination-Augmented-Agents-for-Deep-Reinforcement-Learning.html
index b9827c2e..b6ec8c9b 100644
--- a/Imagination-Augmented-Agents-for-Deep-Reinforcement-Learning.html
+++ b/Imagination-Augmented-Agents-for-Deep-Reinforcement-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -273,9 +273,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Improving-Information-Extraction-by-Acquiring-External-Evidence-with-Reinforcement-Learning.html b/Improving-Information-Extraction-by-Acquiring-External-Evidence-with-Reinforcement-Learning.html
index 5e3119e0..d2121df1 100644
--- a/Improving-Information-Extraction-by-Acquiring-External-Evidence-with-Reinforcement-Learning.html
+++ b/Improving-Information-Extraction-by-Acquiring-External-Evidence-with-Reinforcement-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -311,9 +311,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Kronecker-Recurrent-Units.html b/Kronecker-Recurrent-Units.html
index 2b1bd236..6761d0f1 100644
--- a/Kronecker-Recurrent-Units.html
+++ b/Kronecker-Recurrent-Units.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -347,9 +347,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Large-Memory-Layers-with-Product-Keys.html b/Large-Memory-Layers-with-Product-Keys.html
index 6050b548..8bc05b1d 100644
--- a/Large-Memory-Layers-with-Product-Keys.html
+++ b/Large-Memory-Layers-with-Product-Keys.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -296,9 +296,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Learned-Optimizers-that-Scale-and-Generalize.html b/Learned-Optimizers-that-Scale-and-Generalize.html
index 46de6169..6ed5b0d5 100644
--- a/Learned-Optimizers-that-Scale-and-Generalize.html
+++ b/Learned-Optimizers-that-Scale-and-Generalize.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -261,9 +261,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Learning-Explanations-That-Are-Hard-To-Vary.html b/Learning-Explanations-That-Are-Hard-To-Vary.html
index f63a6e16..2b4ec987 100644
--- a/Learning-Explanations-That-Are-Hard-To-Vary.html
+++ b/Learning-Explanations-That-Are-Hard-To-Vary.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -277,9 +277,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Learning-Independent-Causal-Mechanisms.html b/Learning-Independent-Causal-Mechanisms.html
index 22f8da09..1d6f2de1 100644
--- a/Learning-Independent-Causal-Mechanisms.html
+++ b/Learning-Independent-Causal-Mechanisms.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -315,9 +315,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Learning-a-SAT-Solver-from-Single-Bit-Supervision.html b/Learning-a-SAT-Solver-from-Single-Bit-Supervision.html
index 988defc6..856a2b12 100644
--- a/Learning-a-SAT-Solver-from-Single-Bit-Supervision.html
+++ b/Learning-a-SAT-Solver-from-Single-Bit-Supervision.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -286,9 +286,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Learning-to-Compute-Word-Embeddings-On-the-Fly.html b/Learning-to-Compute-Word-Embeddings-On-the-Fly.html
index 5aff02dc..b10a64a1 100644
--- a/Learning-to-Compute-Word-Embeddings-On-the-Fly.html
+++ b/Learning-to-Compute-Word-Embeddings-On-the-Fly.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -270,9 +270,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Learning-to-Count-Objects-in-Natural-Images-for-Visual-Question-Answering.html b/Learning-to-Count-Objects-in-Natural-Images-for-Visual-Question-Answering.html
index 6bedefa9..46ea69b0 100644
--- a/Learning-to-Count-Objects-in-Natural-Images-for-Visual-Question-Answering.html
+++ b/Learning-to-Count-Objects-in-Natural-Images-for-Visual-Question-Answering.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -265,9 +265,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Linguistic-Knowledge-as-Memory-for-Recurrent-Neural-Networks.html b/Linguistic-Knowledge-as-Memory-for-Recurrent-Neural-Networks.html
index 4af0b113..09be790c 100644
--- a/Linguistic-Knowledge-as-Memory-for-Recurrent-Neural-Networks.html
+++ b/Linguistic-Knowledge-as-Memory-for-Recurrent-Neural-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -250,9 +250,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/MONet-Unsupervised-Scene-Decomposition-and-Representation.html b/MONet-Unsupervised-Scene-Decomposition-and-Representation.html
index 1823b6fc..1f81afa1 100644
--- a/MONet-Unsupervised-Scene-Decomposition-and-Representation.html
+++ b/MONet-Unsupervised-Scene-Decomposition-and-Representation.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -282,9 +282,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Making-the-V-in-VQA-Matter-Elevating-the-Role-of-Image-Understanding-in-Visual-Question-Answering.html b/Making-the-V-in-VQA-Matter-Elevating-the-Role-of-Image-Understanding-in-Visual-Question-Answering.html
index 6724876c..e815ad86 100644
--- a/Making-the-V-in-VQA-Matter-Elevating-the-Role-of-Image-Understanding-in-Visual-Question-Answering.html
+++ b/Making-the-V-in-VQA-Matter-Elevating-the-Role-of-Image-Understanding-in-Visual-Question-Answering.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -229,9 +229,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Massively-Multilingual-Neural-Machine-Translation-in-the-Wild-Findings-and-Challenges.html b/Massively-Multilingual-Neural-Machine-Translation-in-the-Wild-Findings-and-Challenges.html
index 54c2bb28..7c8ad86d 100644
--- a/Massively-Multilingual-Neural-Machine-Translation-in-the-Wild-Findings-and-Challenges.html
+++ b/Massively-Multilingual-Neural-Machine-Translation-in-the-Wild-Findings-and-Challenges.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -370,9 +370,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Mastering-Atari,-Go,-Chess-and-Shogi-by-Planning-with-a-Learned-Model.html b/Mastering-Atari,-Go,-Chess-and-Shogi-by-Planning-with-a-Learned-Model.html
index 0a41d683..78940be8 100644
--- a/Mastering-Atari,-Go,-Chess-and-Shogi-by-Planning-with-a-Learned-Model.html
+++ b/Mastering-Atari,-Go,-Chess-and-Shogi-by-Planning-with-a-Learned-Model.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -312,9 +312,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Measuring-Abstract-Reasoning-in-Neural-Networks.html b/Measuring-Abstract-Reasoning-in-Neural-Networks.html
index a2911d64..cd1bff3b 100644
--- a/Measuring-Abstract-Reasoning-in-Neural-Networks.html
+++ b/Measuring-Abstract-Reasoning-in-Neural-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -356,9 +356,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Memory-Based-Parameter-Adaption.html b/Memory-Based-Parameter-Adaption.html
index fbce13fa..59ccefb4 100644
--- a/Memory-Based-Parameter-Adaption.html
+++ b/Memory-Based-Parameter-Adaption.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -337,9 +337,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Meta-Learning-Update-Rules-for-Unsupervised-Representation-Learning.html b/Meta-Learning-Update-Rules-for-Unsupervised-Representation-Learning.html
index 432b6a1a..a126e8c7 100644
--- a/Meta-Learning-Update-Rules-for-Unsupervised-Representation-Learning.html
+++ b/Meta-Learning-Update-Rules-for-Unsupervised-Representation-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -313,9 +313,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Meta-Reinforcement-Learning-of-Structured-Exploration-Strategies.html b/Meta-Reinforcement-Learning-of-Structured-Exploration-Strategies.html
index e18c665f..9d50c46a 100644
--- a/Meta-Reinforcement-Learning-of-Structured-Exploration-Strategies.html
+++ b/Meta-Reinforcement-Learning-of-Structured-Exploration-Strategies.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -283,9 +283,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Model-Primitive-Hierarchical-Lifelong-Reinforcement-Learning.html b/Model-Primitive-Hierarchical-Lifelong-Reinforcement-Learning.html
index 559f8a9d..15a2c127 100644
--- a/Model-Primitive-Hierarchical-Lifelong-Reinforcement-Learning.html
+++ b/Model-Primitive-Hierarchical-Lifelong-Reinforcement-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -355,9 +355,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Modular-meta-learning.html b/Modular-meta-learning.html
index 8ac6ac07..da24f581 100644
--- a/Modular-meta-learning.html
+++ b/Modular-meta-learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -387,9 +387,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Multiple-Model-Based-Reinforcement-Learning.html b/Multiple-Model-Based-Reinforcement-Learning.html
index fadcdae7..19ff1ef3 100644
--- a/Multiple-Model-Based-Reinforcement-Learning.html
+++ b/Multiple-Model-Based-Reinforcement-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -247,9 +247,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Net2Net-Accelerating-Learning-via-Knowledge-Transfer.html b/Net2Net-Accelerating-Learning-via-Knowledge-Transfer.html
index e6962305..c2f9d4e9 100644
--- a/Net2Net-Accelerating-Learning-via-Knowledge-Transfer.html
+++ b/Net2Net-Accelerating-Learning-via-Knowledge-Transfer.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -260,9 +260,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Network-Motifs-Simple-Building-Blocks-of-Complex-Networks.html b/Network-Motifs-Simple-Building-Blocks-of-Complex-Networks.html
index fe70e52b..7f8a6662 100644
--- a/Network-Motifs-Simple-Building-Blocks-of-Complex-Networks.html
+++ b/Network-Motifs-Simple-Building-Blocks-of-Complex-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -225,9 +225,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Network-Randomization-A-Simple-Technique-for-Generalization-in-Deep-Reinforcement-Learning.html b/Network-Randomization-A-Simple-Technique-for-Generalization-in-Deep-Reinforcement-Learning.html
index 27c5d6d3..afa67553 100644
--- a/Network-Randomization-A-Simple-Technique-for-Generalization-in-Deep-Reinforcement-Learning.html
+++ b/Network-Randomization-A-Simple-Technique-for-Generalization-in-Deep-Reinforcement-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -269,9 +269,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Neural-Message-Passing-for-Quantum-Chemistry.html b/Neural-Message-Passing-for-Quantum-Chemistry.html
index 602aacef..44512089 100644
--- a/Neural-Message-Passing-for-Quantum-Chemistry.html
+++ b/Neural-Message-Passing-for-Quantum-Chemistry.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -353,9 +353,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Neural-Module-Networks.html b/Neural-Module-Networks.html
index 2e5e190b..8132f6ed 100644
--- a/Neural-Module-Networks.html
+++ b/Neural-Module-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -265,9 +265,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Neural-Relational-Inference-for-Interacting-Systems.html b/Neural-Relational-Inference-for-Interacting-Systems.html
index e614b4cb..9c0e0cc8 100644
--- a/Neural-Relational-Inference-for-Interacting-Systems.html
+++ b/Neural-Relational-Inference-for-Interacting-Systems.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -288,9 +288,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Observational-Overfitting-in-Reinforcement-Learning.html b/Observational-Overfitting-in-Reinforcement-Learning.html
index 327d713a..9ecc42c9 100644
--- a/Observational-Overfitting-in-Reinforcement-Learning.html
+++ b/Observational-Overfitting-in-Reinforcement-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -325,9 +325,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/On-the-Difficulty-of-Warm-Starting-Neural-Network-Training.html b/On-the-Difficulty-of-Warm-Starting-Neural-Network-Training.html
index 9067c9a1..95fe0f48 100644
--- a/On-the-Difficulty-of-Warm-Starting-Neural-Network-Training.html
+++ b/On-the-Difficulty-of-Warm-Starting-Neural-Network-Training.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -327,9 +327,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/One-Model-To-Learn-Them-All.html b/One-Model-To-Learn-Them-All.html
index 69c1a892..f819b729 100644
--- a/One-Model-To-Learn-Them-All.html
+++ b/One-Model-To-Learn-Them-All.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -368,9 +368,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/One-Solution-is-Not-All-You-Need-Few-Shot-Extrapolation-via-Structured-MaxEnt-RL.html b/One-Solution-is-Not-All-You-Need-Few-Shot-Extrapolation-via-Structured-MaxEnt-RL.html
index 9de6b7c7..b9912531 100644
--- a/One-Solution-is-Not-All-You-Need-Few-Shot-Extrapolation-via-Structured-MaxEnt-RL.html
+++ b/One-Solution-is-Not-All-You-Need-Few-Shot-Extrapolation-via-Structured-MaxEnt-RL.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -310,9 +310,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/One-shot-Learning-with-Memory-Augmented-Neural-Networks.html b/One-shot-Learning-with-Memory-Augmented-Neural-Networks.html
index 9a0561df..294e295c 100644
--- a/One-shot-Learning-with-Memory-Augmented-Neural-Networks.html
+++ b/One-shot-Learning-with-Memory-Augmented-Neural-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -312,9 +312,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Outrageously-Large-Neural-Networks-The-Sparsely-Gated-Mixture-of-Experts-Layer.html b/Outrageously-Large-Neural-Networks-The-Sparsely-Gated-Mixture-of-Experts-Layer.html
index 8e6ff74a..ef5bdf72 100644
--- a/Outrageously-Large-Neural-Networks-The-Sparsely-Gated-Mixture-of-Experts-Layer.html
+++ b/Outrageously-Large-Neural-Networks-The-Sparsely-Gated-Mixture-of-Experts-Layer.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -334,9 +334,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/PHYRE-A-New-Benchmark-for-Physical-Reasoning.html b/PHYRE-A-New-Benchmark-for-Physical-Reasoning.html
index 0aec0e60..fe6953f3 100644
--- a/PHYRE-A-New-Benchmark-for-Physical-Reasoning.html
+++ b/PHYRE-A-New-Benchmark-for-Physical-Reasoning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -355,9 +355,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/PTE-Predictive-Text-Embedding-through-Large-scale-Heterogeneous-Text-Networks.html b/PTE-Predictive-Text-Embedding-through-Large-scale-Heterogeneous-Text-Networks.html
index 62820c48..47841bc7 100644
--- a/PTE-Predictive-Text-Embedding-through-Large-scale-Heterogeneous-Text-Networks.html
+++ b/PTE-Predictive-Text-Embedding-through-Large-scale-Heterogeneous-Text-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -288,9 +288,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Poincare-Embeddings-for-Learning-Hierarchical-Representations.html b/Poincare-Embeddings-for-Learning-Hierarchical-Representations.html
index 7e96524e..6e040b44 100644
--- a/Poincare-Embeddings-for-Learning-Hierarchical-Representations.html
+++ b/Poincare-Embeddings-for-Learning-Hierarchical-Representations.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -321,9 +321,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Pointer-Networks.html b/Pointer-Networks.html
index 4c7fcd53..fa354a43 100644
--- a/Pointer-Networks.html
+++ b/Pointer-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -255,9 +255,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Practical-Lessons-from-Predicting-Clicks-on-Ads-at-Facebook.html b/Practical-Lessons-from-Predicting-Clicks-on-Ads-at-Facebook.html
index df43e04b..d5736553 100644
--- a/Practical-Lessons-from-Predicting-Clicks-on-Ads-at-Facebook.html
+++ b/Practical-Lessons-from-Predicting-Clicks-on-Ads-at-Facebook.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -371,9 +371,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Pre-training-Graph-Neural-Networks-with-Kernels.html b/Pre-training-Graph-Neural-Networks-with-Kernels.html
index 79454862..46b8be1d 100644
--- a/Pre-training-Graph-Neural-Networks-with-Kernels.html
+++ b/Pre-training-Graph-Neural-Networks-with-Kernels.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -264,9 +264,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Principled-Detection-of-Out-of-Distribution-Examples-in-Neural-Networks.html b/Principled-Detection-of-Out-of-Distribution-Examples-in-Neural-Networks.html
index 014f7123..649c1757 100644
--- a/Principled-Detection-of-Out-of-Distribution-Examples-in-Neural-Networks.html
+++ b/Principled-Detection-of-Out-of-Distribution-Examples-in-Neural-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -311,9 +311,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Quantifying-Generalization-in-Reinforcement-Learning.html b/Quantifying-Generalization-in-Reinforcement-Learning.html
index 159e39ad..24472777 100644
--- a/Quantifying-Generalization-in-Reinforcement-Learning.html
+++ b/Quantifying-Generalization-in-Reinforcement-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -319,9 +319,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/R-NET-Machine-Reading-Comprehension-with-Self-matching-Networks.html b/R-NET-Machine-Reading-Comprehension-with-Self-matching-Networks.html
index 72ad4c35..a875ced3 100644
--- a/R-NET-Machine-Reading-Comprehension-with-Self-matching-Networks.html
+++ b/R-NET-Machine-Reading-Comprehension-with-Self-matching-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -281,9 +281,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Rapid-Learning-or-Feature-Reuse-Towards-Understanding-the-Effectiveness-of-MAML.html b/Rapid-Learning-or-Feature-Reuse-Towards-Understanding-the-Effectiveness-of-MAML.html
index 90a17257..57a1c51c 100644
--- a/Rapid-Learning-or-Feature-Reuse-Towards-Understanding-the-Effectiveness-of-MAML.html
+++ b/Rapid-Learning-or-Feature-Reuse-Towards-Understanding-the-Effectiveness-of-MAML.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -332,9 +332,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Reading-Wikipedia-to-Answer-Open-Domain-Questions.html b/Reading-Wikipedia-to-Answer-Open-Domain-Questions.html
index 33a9c218..f1dc2bd1 100644
--- a/Reading-Wikipedia-to-Answer-Open-Domain-Questions.html
+++ b/Reading-Wikipedia-to-Answer-Open-Domain-Questions.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -265,9 +265,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/ReasoNet-Learning-to-Stop-Reading-in-Machine-Comprehension.html b/ReasoNet-Learning-to-Stop-Reading-in-Machine-Comprehension.html
index 6f80ebbb..4fe04e8c 100644
--- a/ReasoNet-Learning-to-Stop-Reading-in-Machine-Comprehension.html
+++ b/ReasoNet-Learning-to-Stop-Reading-in-Machine-Comprehension.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -320,9 +320,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Refining-Source-Representations-with-Relation-Networks-for-Neural-Machine-Translation.html b/Refining-Source-Representations-with-Relation-Networks-for-Neural-Machine-Translation.html
index 99e72c2f..06de16da 100644
--- a/Refining-Source-Representations-with-Relation-Networks-for-Neural-Machine-Translation.html
+++ b/Refining-Source-Representations-with-Relation-Networks-for-Neural-Machine-Translation.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -276,9 +276,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Relational-Reinforcement-Learning.html b/Relational-Reinforcement-Learning.html
index 84a6dd06..786ce34c 100644
--- a/Relational-Reinforcement-Learning.html
+++ b/Relational-Reinforcement-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -312,9 +312,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Remembering-for-the-Right-Reasons-Explanations-Reduce-Catastrophic-Forgetting.html b/Remembering-for-the-Right-Reasons-Explanations-Reduce-Catastrophic-Forgetting.html
index d2f5ddc2..a51729c6 100644
--- a/Remembering-for-the-Right-Reasons-Explanations-Reduce-Catastrophic-Forgetting.html
+++ b/Remembering-for-the-Right-Reasons-Explanations-Reduce-Catastrophic-Forgetting.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -254,9 +254,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Representation-Tradeoffs-for-Hyperbolic-Embeddings.html b/Representation-Tradeoffs-for-Hyperbolic-Embeddings.html
index ce1e5d2a..4b5e40c9 100644
--- a/Representation-Tradeoffs-for-Hyperbolic-Embeddings.html
+++ b/Representation-Tradeoffs-for-Hyperbolic-Embeddings.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -372,9 +372,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Revisiting-Fundamentals-of-Experience-Replay.html b/Revisiting-Fundamentals-of-Experience-Replay.html
index ce323de3..e0ef9d80 100644
--- a/Revisiting-Fundamentals-of-Experience-Replay.html
+++ b/Revisiting-Fundamentals-of-Experience-Replay.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -321,9 +321,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Revisiting-Semi-Supervised-Learning-with-Graph-Embeddings.html b/Revisiting-Semi-Supervised-Learning-with-Graph-Embeddings.html
index 283721b6..15e86184 100644
--- a/Revisiting-Semi-Supervised-Learning-with-Graph-Embeddings.html
+++ b/Revisiting-Semi-Supervised-Learning-with-Graph-Embeddings.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -277,9 +277,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Searching-for-Build-Debt-Experiences-Managing-Technical-Debt-at-Google.html b/Searching-for-Build-Debt-Experiences-Managing-Technical-Debt-at-Google.html
index ddac935c..afe366ec 100644
--- a/Searching-for-Build-Debt-Experiences-Managing-Technical-Debt-at-Google.html
+++ b/Searching-for-Build-Debt-Experiences-Managing-Technical-Debt-at-Google.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -331,9 +331,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Set-Transformer-A-Framework-for-Attention-based-Permutation-Invariant-Neural-Networks.html b/Set-Transformer-A-Framework-for-Attention-based-Permutation-Invariant-Neural-Networks.html
index 5ff6e317..20676569 100644
--- a/Set-Transformer-A-Framework-for-Attention-based-Permutation-Invariant-Neural-Networks.html
+++ b/Set-Transformer-A-Framework-for-Attention-based-Permutation-Invariant-Neural-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -294,9 +294,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Simple-Baseline-for-Visual-Question-Answering.html b/Simple-Baseline-for-Visual-Question-Answering.html
index 9046e8d4..0c3942e1 100644
--- a/Simple-Baseline-for-Visual-Question-Answering.html
+++ b/Simple-Baseline-for-Visual-Question-Answering.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -225,9 +225,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Smooth-Loss-Functions-for-Deep-Top-k-Classification.html b/Smooth-Loss-Functions-for-Deep-Top-k-Classification.html
index 5ae12ff1..8897f48c 100644
--- a/Smooth-Loss-Functions-for-Deep-Top-k-Classification.html
+++ b/Smooth-Loss-Functions-for-Deep-Top-k-Classification.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -308,9 +308,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/StarSpace-Embed-All-The-Things.html b/StarSpace-Embed-All-The-Things.html
index 926be811..3bbfee59 100644
--- a/StarSpace-Embed-All-The-Things.html
+++ b/StarSpace-Embed-All-The-Things.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -248,9 +248,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Stylistic-Transfer-in-Natural-Language-Generation-Systems-Using-Recurrent-Neural-Networks.html b/Stylistic-Transfer-in-Natural-Language-Generation-Systems-Using-Recurrent-Neural-Networks.html
index 84713dcd..2465c4c9 100644
--- a/Stylistic-Transfer-in-Natural-Language-Generation-Systems-Using-Recurrent-Neural-Networks.html
+++ b/Stylistic-Transfer-in-Natural-Language-Generation-Systems-Using-Recurrent-Neural-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -239,9 +239,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Superposition-of-many-models-into-one.html b/Superposition-of-many-models-into-one.html
index 7e8ee5de..8339a9bc 100644
--- a/Superposition-of-many-models-into-one.html
+++ b/Superposition-of-many-models-into-one.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -376,9 +376,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Supervised-Contrastive-Learning.html b/Supervised-Contrastive-Learning.html
index 9259a134..88500268 100644
--- a/Supervised-Contrastive-Learning.html
+++ b/Supervised-Contrastive-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -301,9 +301,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Swish-A-self-gated-activation-function.html b/Swish-A-self-gated-activation-function.html
index 13812477..56e10b63 100644
--- a/Swish-A-self-gated-activation-function.html
+++ b/Swish-A-self-gated-activation-function.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -236,9 +236,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Synthesized-Policies-for-Transfer-and-Adaptation-across-Tasks-and-Environments.html b/Synthesized-Policies-for-Transfer-and-Adaptation-across-Tasks-and-Environments.html
index 6af90235..8ea213a9 100644
--- a/Synthesized-Policies-for-Transfer-and-Adaptation-across-Tasks-and-Environments.html
+++ b/Synthesized-Policies-for-Transfer-and-Adaptation-across-Tasks-and-Environments.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -383,9 +383,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/TASKNORM-Rethinking-Batch-Normalization-for-Meta-Learning.html b/TASKNORM-Rethinking-Batch-Normalization-for-Meta-Learning.html
index 94095cff..f33257bc 100644
--- a/TASKNORM-Rethinking-Batch-Normalization-for-Meta-Learning.html
+++ b/TASKNORM-Rethinking-Batch-Normalization-for-Meta-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -359,9 +359,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Task-Oriented-Query-Reformulation-with-Reinforcement-Learning.html b/Task-Oriented-Query-Reformulation-with-Reinforcement-Learning.html
index f1e78ae0..45162c91 100644
--- a/Task-Oriented-Query-Reformulation-with-Reinforcement-Learning.html
+++ b/Task-Oriented-Query-Reformulation-with-Reinforcement-Learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -305,9 +305,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/The-Lottery-Ticket-Hypothesis-Training-Pruned-Neural-Networks.html b/The-Lottery-Ticket-Hypothesis-Training-Pruned-Neural-Networks.html
index c21704af..29f8b3af 100644
--- a/The-Lottery-Ticket-Hypothesis-Training-Pruned-Neural-Networks.html
+++ b/The-Lottery-Ticket-Hypothesis-Training-Pruned-Neural-Networks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -263,9 +263,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/The-Tail-at-Scale.html b/The-Tail-at-Scale.html
index bdf2ebd7..9870e301 100644
--- a/The-Tail-at-Scale.html
+++ b/The-Tail-at-Scale.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -375,9 +375,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/To-Tune-or-Not-to-Tune-Adapting-Pretrained-Representations-to-Diverse-Tasks.html b/To-Tune-or-Not-to-Tune-Adapting-Pretrained-Representations-to-Diverse-Tasks.html
index 07e95b64..30b12d0d 100644
--- a/To-Tune-or-Not-to-Tune-Adapting-Pretrained-Representations-to-Diverse-Tasks.html
+++ b/To-Tune-or-Not-to-Tune-Adapting-Pretrained-Representations-to-Diverse-Tasks.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -337,9 +337,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools.html b/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools.html
new file mode 100644
index 00000000..7efa3fed
--- /dev/null
+++ b/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools.html
@@ -0,0 +1,488 @@
+<!DOCTYPE html>
+<html lang="en-us">
+  
+  <script type="text/x-mathjax-config">
+MathJax.Hub.Config({
+  tex2jax: {
+    inlineMath: [['$','$'], ['\\(','\\)']],
+    processEscapes: true
+  }
+});
+</script>
+<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML" type="text/javascript"></script>
+
+  <head>
+  <link href="http://gmpg.org/xfn/11" rel="profile">
+  <meta http-equiv="X-UA-Compatible" content="IE=edge">
+  <meta http-equiv="content-type" content="text/html; charset=utf-8">
+
+  <!-- Enable responsiveness on mobile devices-->
+  <meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1">
+
+  <title>
+    
+      Toolformer - Language Models Can Teach Themselves to Use Tools &middot; Papers I Read
+    
+  </title>
+
+  <!-- CSS -->
+  <link rel="stylesheet" href="https://shagunsodhani.github.io/papers-I-read/public/css/poole.css">
+  <link rel="stylesheet" href="https://shagunsodhani.github.io/papers-I-read/public/css/syntax.css">
+  <link rel="stylesheet" href="https://shagunsodhani.github.io/papers-I-read/public/css/lanyon.css">
+  <link rel="stylesheet" href="https://shagunsodhani.github.io/papers-I-read/public/css/style.css">
+  <link rel="stylesheet" href="https://shagunsodhani.github.io/papers-I-read/public/font-awesome-4.7.0/css/font-awesome.css">
+
+  <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=PT+Serif:400,400italic,700%7CPT+Sans:400">
+
+  <!-- Icons -->
+  <link rel="apple-touch-icon-precomposed" sizes="144x144" href="https://shagunsodhani.github.io/papers-I-read/public/apple-touch-icon-precomposed.png">
+  <link rel="shortcut icon" href="https://shagunsodhani.github.io/papers-I-read/public/favicon.ico">
+
+  <!-- RSS -->
+  <link rel="alternate" type="application/rss+xml" title="RSS" href="/atom.xml">
+</head>
+
+  <!-- Global site tag (gtag.js) - Google Analytics -->
+<script async src="https://www.googletagmanager.com/gtag/js?id=UA-68140113-4"></script>
+<script>
+  window.dataLayer = window.dataLayer || [];
+  function gtag(){dataLayer.push(arguments);}
+  gtag('js', new Date());
+
+  gtag('config', 'UA-68140113-4');
+</script>
+
+
+  <body>
+
+    <!-- Target for toggling the sidebar `.sidebar-checkbox` is for regular
+     styles, `#sidebar-checkbox` for behavior. -->
+<input type="checkbox" class="sidebar-checkbox" id="sidebar-checkbox">
+
+<!-- Toggleable sidebar -->
+<div class="sidebar" id="sidebar">
+  <div class="sidebar-item">
+    <p>I am trying a new initiative - <i>A Paper A Week</i>. This blog will hold all the notes and summaries.</p>
+  </div>
+
+  <nav class="sidebar-nav">
+    <a class="sidebar-nav-item" href="https://shagunsodhani.github.io/papers-I-read/">Home</a>
+
+    
+
+    
+    
+      
+        
+      
+    
+      
+        
+      
+    
+      
+        
+          <a class="sidebar-nav-item" href="https://shagunsodhani.github.io/papers-I-read/archieve">Archive</a>
+        
+      
+    
+      
+    
+      
+        
+      
+    
+      
+        
+      
+    
+      
+        
+      
+    
+      
+        
+      
+    
+      
+        
+      
+    
+      
+        
+      
+    
+      
+        
+      
+    
+      
+        
+      
+    
+      
+        
+      
+    
+      
+        
+      
+    
+      
+        
+      
+    
+      
+        
+      
+    
+      
+        
+      
+    
+      
+        
+      
+    
+      
+        
+          <a class="sidebar-nav-item" href="https://shagunsodhani.github.io/papers-I-read/tags">Tags</a>
+        
+      
+    
+
+    <!-- <a class="sidebar-nav-item" href="https://github.com/shagunsodhani/papers-I-read/archive/v1.0.0.zip">Download</a> -->
+    <a class="sidebar-nav-item" href="https://github.com/shagunsodhani/papers-I-read">GitHub project</a>
+    <a class="sidebar-nav-item" href="https://shagunsodhani.github.io/papers-I-read/atom.xml">Feed</a>
+    <!-- <span class="sidebar-nav-item">Currently v1.0.0</span> -->
+  </nav>
+
+  <div class="sidebar-item">
+    <p>
+      &copy; 2023. All rights reserved.
+    </p>
+  </div>
+</div>
+
+
+    <!-- Wrap is the content to shift when toggling the sidebar. We wrap the
+         content to avoid any CSS collisions with our real content. -->
+    <div class="wrap">
+      <div class="masthead">
+        <div class="container">
+          <h3 class="masthead-title">
+            <a href="https://shagunsodhani.github.io/papers-I-read/" title="Home">Papers I Read</a>
+            <small>Notes and Summaries</small>
+          </h3>
+        </div>
+      </div>
+
+      <div class="container content">
+        <div class="post">
+  <h1 class="post-title">Toolformer - Language Models Can Teach Themselves to Use Tools</h1>
+  <p class="entry-tags"><a href="https://shagunsodhani.github.io/papers-I-read/tags.html#2023" title="Pages tagged 2023" rel="tag">2023</a> &bull; <a href="https://shagunsodhani.github.io/papers-I-read/tags.html#Large+Language+Model" title="Pages tagged Large Language Model" rel="tag">Large Language Model</a> &bull; <a href="https://shagunsodhani.github.io/papers-I-read/tags.html#PreTrained+Langauge+Model" title="Pages tagged PreTrained Langauge Model" rel="tag">PreTrained Langauge Model</a> &bull; <a href="https://shagunsodhani.github.io/papers-I-read/tags.html#AI" title="Pages tagged AI" rel="tag">AI</a> &bull; <a href="https://shagunsodhani.github.io/papers-I-read/tags.html#GPT" title="Pages tagged GPT" rel="tag">GPT</a> &bull; <a href="https://shagunsodhani.github.io/papers-I-read/tags.html#LLM" title="Pages tagged LLM" rel="tag">LLM</a> &bull; <a href="https://shagunsodhani.github.io/papers-I-read/tags.html#OPT" title="Pages tagged OPT" rel="tag">OPT</a></p>
+  <span class="post-date">10 Feb 2023</span>
+  <h2 id="introduction">Introduction</h2>
+
+<ul>
+  <li>
+    <p>The paper presents Toolformer, a language model that uses simple APIs to use external tools (calculator, QA system, search engine, translation system, and calendar).</p>
+  </li>
+  <li>
+    <p><a href="https://arxiv.org/abs/2302.04761">Link to the paper</a></p>
+  </li>
+</ul>
+
+<h2 id="approach">Approach</h2>
+
+<ul>
+  <li>
+    <p>Starting with a language model, M, the goal is to enable the language model to use tools by invoking API calls.</p>
+  </li>
+  <li>
+    <p>An API call is denoted by the tuple $c = (api_name, api_input)$. It can be linearized as $e(c) = [api_name(api_input)]$ or as $e(c, r) = [api_name(api_input) -&gt; r]$ where $r$ denotes the result of the API.</p>
+  </li>
+  <li>
+    <p>The given dataset of plain text, $C$, is converted into a dataset $C*$ augmented with the API calls using a three-step process.</p>
+  </li>
+  <li>
+    <p>In the first step, a position ($i$) and API call candidates (for the position $i$) are sampled.</p>
+
+    <ul>
+      <li>
+        <p>Positions are sampled by (i) computing the probability that M assigns to starting an API call for each position and (ii) retaining the top-$k$ positions with a probability greater than a threshold value.</p>
+      </li>
+      <li>
+        <p>For each of the sampled positions (say $i$), API calls are sampled by concatenating a prompt to the tokens till index $i$ and sampling from the model M. Examples that do not generate the “end of the API” token (i.e.,”]”) are discarded.</p>
+      </li>
+    </ul>
+  </li>
+  <li>
+    <p>In the second step, the API calls are executed to obtain response $r$ (text sequence).</p>
+
+    <ul>
+      <li>API calls are filtered using the following criteria: if providing M with both the input and the output of the API makes it easier for M to predict the future token, compared to not using the API call at all or just using the input to the API, then the API call is helpful for M, and the example should be retained.</li>
+    </ul>
+  </li>
+  <li>
+    <p>In the last step, the remaining API calls are merged to obtain the augmented dataset $C*$ that is used for finetuning M.</p>
+  </li>
+  <li>
+    <p>Note that $C*$ contains $C$, so M is finetuned on the original dataset and examples where a tool is helpful.</p>
+  </li>
+  <li>
+    <p>During inference, the model is used for decoding in the usual way. Decoding is stopped when it produces the “-&gt;” token, and the corresponding API is used to generate the response. The decoding process (using the model) resumes with the API output appended to the decoded text.</p>
+  </li>
+</ul>
+
+<h2 id="tools">Tools</h2>
+
+<ul>
+  <li>
+    <p>There are two constraints on the tools: (i) their input and output should be expressible as text, and (ii) few demonstrations can be obtained from the tools. The second constraint means that the tool should be useable or accessible.</p>
+  </li>
+  <li>
+    <p>The paper considered the following tools: a question-answering system, a Wikipedia search engine, a calculator, a calendar, and a machine translation system. Of these, only the calculator and calendar are non-neural network tools.</p>
+  </li>
+</ul>
+
+<h2 id="experiments">Experiments</h2>
+
+<ul>
+  <li>
+    <p>Subset of CCNet is used as the language modeling dataset.</p>
+  </li>
+  <li>
+    <p>GPT-J is used as the language model.</p>
+  </li>
+  <li>
+    <p>For finetuning, the batch size is 128, the learning rate is 1e-5, and a linear warmup for the first 10% of training is used.</p>
+  </li>
+  <li>
+    <p>Following models are compared:</p>
+
+    <ul>
+      <li>
+        <p>GPT-J: Regular GPT-J model without any finetuning.</p>
+      </li>
+      <li>
+        <p>GPT-J + CC: GPT-J finetuned on $C$ without any API calls.</p>
+      </li>
+      <li>
+        <p>Toolformer, i.e. GPT-J finetuned on $C*$.</p>
+      </li>
+      <li>
+        <p>Toolformer with API calls disabled during training.</p>
+      </li>
+      <li>
+        <p>OPT 66B</p>
+      </li>
+      <li>
+        <p>GPT-3</p>
+      </li>
+    </ul>
+  </li>
+  <li>
+    <p>The models are evaluated in the prompted zero-shot setup, where models are instructed to solve a task without any in-context examples.</p>
+  </li>
+  <li>
+    <p>One difference from the standard greedy decoding is that the API call is used whenever it is one of the top-10 most likely next tokens. This is done to increase the use of API calls.</p>
+  </li>
+  <li>
+    <p>Evaluation Tasks</p>
+
+    <ul>
+      <li>
+        <p>SQuAD, GoogleRE, and T-REx subsets of the LAMA benchmark where the model has to complete a short statement with a missing fact.</p>
+
+        <ul>
+          <li>
+            <p>Since LAMA questions are based on Wikipedia, Toolformer isn’t allowed to use Wikipedia search.</p>
+          </li>
+          <li>
+            <p>The evaluation criteria is to check if the correct word is among the first five words predicted by the model.</p>
+          </li>
+          <li>
+            <p>Toolformer uses the question-answering tool for most cases, outperforming all the baselines.</p>
+          </li>
+        </ul>
+      </li>
+      <li>
+        <p>Math Dataset</p>
+
+        <ul>
+          <li>
+            <p>eSDiv, SVAMP, and MAWPS benchmarks.</p>
+          </li>
+          <li>
+            <p>The first number predicted by the model is considered to be the output.</p>
+          </li>
+          <li>
+            <p>Toolformer uses the calculator tool for most cases, thereby outperforming all the baselines.</p>
+          </li>
+        </ul>
+      </li>
+      <li>
+        <p>Question Answering</p>
+
+        <ul>
+          <li>
+            <p>Web Questions, Natural Questions, and TriviaQA datasets.</p>
+          </li>
+          <li>
+            <p>The evaluation criteria is to check if the correct word is among the first 20 words predicted by the model.</p>
+          </li>
+          <li>
+            <p>Question Answering tool is disabled for this setup.</p>
+          </li>
+          <li>
+            <p>Toolformer uses the Wikipedia tool for most cases, thereby outperforming all the baselines other than the much larger GPT-3 model.</p>
+          </li>
+        </ul>
+      </li>
+      <li>
+        <p>Multilingual Question Answering</p>
+
+        <ul>
+          <li>
+            <p>MLQA benchmark.</p>
+          </li>
+          <li>
+            <p>The evaluation criteria is to check if the correct word is among the first ten words predicted by the model.</p>
+          </li>
+          <li>
+            <p>Toolformer uses the translation tool for most of the questions, with questions in Hindi being an exception.</p>
+          </li>
+          <li>
+            <p>However, Toolformer does not consistently outperform the GPT-J baseline, likely because, for some languages, finetuning on CCNet could hurt performance.</p>
+          </li>
+        </ul>
+      </li>
+      <li>
+        <p>Temporal Datasets</p>
+
+        <ul>
+          <li>
+            <p>TEMPLAMA (cloze style queries where the answer changes with time) and DATESET (dataset generated through a series of templates and populated with random dates/durations).</p>
+          </li>
+          <li>
+            <p>While Toolformer outperforms the baselines for both datasets, it relies on the Wikipedia search and Question Answering tools (and not the calendar tool) for the LAMA dataset. On the DATESET dataset, it uses the calendar tool in the majority.</p>
+          </li>
+        </ul>
+      </li>
+      <li>
+        <p>Language Modeling</p>
+
+        <ul>
+          <li>
+            <p>WikiText and a subset of 10,000 randomly selected documents from CCNet (not used during training of M).</p>
+          </li>
+          <li>
+            <p>Training on $C*$ does not increase perplexity (compared to training on C). In this experiment, the API calls are disabled during inference.</p>
+          </li>
+        </ul>
+      </li>
+    </ul>
+  </li>
+  <li>
+    <p>Varying the size of the underlying models show that the ability to use tools emerges only around 755M parameters.</p>
+  </li>
+</ul>
+
+<h2 id="future-work">Future Work</h2>
+
+<ul>
+  <li>
+    <p>Extending Toolformer to chain the use of tools and use tools interactively.</p>
+  </li>
+  <li>
+    <p>In some cases, the use of tools is very sample-inefficient.</p>
+  </li>
+  <li>
+    <p>Decision to use a tool does not account for the cost of using the tool.</p>
+  </li>
+</ul>
+
+</div>
+
+<div class="related">
+  <h2>Related Posts</h2>
+  <ul class="related-posts">
+    
+      <li>
+        <h3>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Synthesized-Policies-for-Transfer-and-Adaptation-across-Tasks-and-Environments">
+            Synthesized Policies for Transfer and Adaptation across Tasks and Environments
+            <small>29 Mar 2021</small>
+          </a>
+        </h3>
+      </li>
+    
+      <li>
+        <h3>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Deep-Neural-Networks-for-YouTube-Recommendations">
+            Deep Neural Networks for YouTube Recommendations
+            <small>22 Mar 2021</small>
+          </a>
+        </h3>
+      </li>
+    
+      <li>
+        <h3>
+          <a href="https://shagunsodhani.github.io/papers-I-read/The-Tail-at-Scale">
+            The Tail at Scale
+            <small>15 Mar 2021</small>
+          </a>
+        </h3>
+      </li>
+    
+  </ul>
+</div>
+      </div>
+    </div>
+
+    <label for="sidebar-checkbox" class="sidebar-toggle"></label>
+
+    
+<div id="disqus_thread"></div>
+<script>
+
+/**
+*  RECOMMENDED CONFIGURATION VARIABLES: EDIT AND UNCOMMENT THE SECTION BELOW TO INSERT DYNAMIC VALUES FROM YOUR PLATFORM OR CMS.
+*  LEARN WHY DEFINING THESE VARIABLES IS IMPORTANT: https://disqus.com/admin/universalcode/#configuration-variables*/
+
+var disqus_config = function () {
+this.page.url = "https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools"  // Replace PAGE_URL with your page's canonical URL variable
+this.page.identifier = "/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools"; // Replace PAGE_IDENTIFIER with your page's unique identifier variable
+};
+
+(function() { // DON'T EDIT BELOW THIS LINE
+var d = document, s = d.createElement('script');
+s.src = 'https://papers-i-read.disqus.com/embed.js';
+s.setAttribute('data-timestamp', +new Date());
+(d.head || d.body).appendChild(s);
+})();
+</script>
+<noscript>Please enable JavaScript to view the <a href="https://disqus.com/?ref_noscript">comments powered by Disqus.</a></noscript>
+
+
+    <script>
+      (function(document) {
+        var toggle = document.querySelector('.sidebar-toggle');
+        var sidebar = document.querySelector('#sidebar');
+        var checkbox = document.querySelector('#sidebar-checkbox');
+
+        document.addEventListener('click', function(e) {
+          var target = e.target;
+
+          if(!checkbox.checked ||
+             sidebar.contains(target) ||
+             (target === checkbox || target === toggle)) return;
+
+          checkbox.checked = false;
+        }, false);
+      })(document);
+    </script>
+
+  </body>
+</html>
diff --git a/Towards-a-Unified-Theory-of-State-Abstraction-for-MDPs.html b/Towards-a-Unified-Theory-of-State-Abstraction-for-MDPs.html
index fc942447..1830005d 100644
--- a/Towards-a-Unified-Theory-of-State-Abstraction-for-MDPs.html
+++ b/Towards-a-Unified-Theory-of-State-Abstraction-for-MDPs.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -315,9 +315,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Towards-a-natural-benchmark-for-continual-learning.html b/Towards-a-natural-benchmark-for-continual-learning.html
index 2fc57746..cf5e4619 100644
--- a/Towards-a-natural-benchmark-for-continual-learning.html
+++ b/Towards-a-natural-benchmark-for-continual-learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -242,9 +242,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/TuckER-Tensor-Factorization-for-Knowledge-Graph-Completion.html b/TuckER-Tensor-Factorization-for-Knowledge-Graph-Completion.html
index c281e16b..78a074ee 100644
--- a/TuckER-Tensor-Factorization-for-Knowledge-Graph-Completion.html
+++ b/TuckER-Tensor-Factorization-for-Knowledge-Graph-Completion.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -325,9 +325,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Two-Stage-Synthesis-Networks-for-Transfer-Learning-in-Machine-Comprehension.html b/Two-Stage-Synthesis-Networks-for-Transfer-Learning-in-Machine-Comprehension.html
index 8b970550..3691585d 100644
--- a/Two-Stage-Synthesis-Networks-for-Transfer-Learning-in-Machine-Comprehension.html
+++ b/Two-Stage-Synthesis-Networks-for-Transfer-Learning-in-Machine-Comprehension.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -289,9 +289,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Two-Too-Simple-Adaptations-of-Word2Vec-for-Syntax-Problems.html b/Two-Too-Simple-Adaptations-of-Word2Vec-for-Syntax-Problems.html
index 60e7199b..823e587a 100644
--- a/Two-Too-Simple-Adaptations-of-Word2Vec-for-Syntax-Problems.html
+++ b/Two-Too-Simple-Adaptations-of-Word2Vec-for-Syntax-Problems.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -200,9 +200,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Unsupervised-Learning-By-Predicting-Noise.html b/Unsupervised-Learning-By-Predicting-Noise.html
index 2725b250..5a1ed510 100644
--- a/Unsupervised-Learning-By-Predicting-Noise.html
+++ b/Unsupervised-Learning-By-Predicting-Noise.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -338,9 +338,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/VQA-Visual-Question-Answering.html b/VQA-Visual-Question-Answering.html
index e254db92..142b9072 100644
--- a/VQA-Visual-Question-Answering.html
+++ b/VQA-Visual-Question-Answering.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -297,9 +297,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/What-Does-Classifying-More-Than-10,000-Image-Categories-Tell-Us.html b/What-Does-Classifying-More-Than-10,000-Image-Categories-Tell-Us.html
index e39f6c91..6325ec7d 100644
--- a/What-Does-Classifying-More-Than-10,000-Image-Categories-Tell-Us.html
+++ b/What-Does-Classifying-More-Than-10,000-Image-Categories-Tell-Us.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -235,9 +235,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/When-Do-Curricula-Work.html b/When-Do-Curricula-Work.html
index 373856ca..d23edcff 100644
--- a/When-Do-Curricula-Work.html
+++ b/When-Do-Curricula-Work.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -305,9 +305,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/When-Recurrent-Models-Don-t-Need-To-Be-Recurrent.html b/When-Recurrent-Models-Don-t-Need-To-Be-Recurrent.html
index 605faf51..23bd3ebd 100644
--- a/When-Recurrent-Models-Don-t-Need-To-Be-Recurrent.html
+++ b/When-Recurrent-Models-Don-t-Need-To-Be-Recurrent.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -253,9 +253,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/When-to-use-parametric-models-in-reinforcement-learning.html b/When-to-use-parametric-models-in-reinforcement-learning.html
index c2b3d59b..d69dfb94 100644
--- a/When-to-use-parametric-models-in-reinforcement-learning.html
+++ b/When-to-use-parametric-models-in-reinforcement-learning.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -297,9 +297,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Word-Representations-via-Gaussian-Embedding.html b/Word-Representations-via-Gaussian-Embedding.html
index 76b13ae8..b46053f9 100644
--- a/Word-Representations-via-Gaussian-Embedding.html
+++ b/Word-Representations-via-Gaussian-Embedding.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -253,9 +253,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Your-Classifier-is-Secretly-an-Energy-Based-Model,-and-You-Should-Treat-it-Like-One.html b/Your-Classifier-is-Secretly-an-Energy-Based-Model,-and-You-Should-Treat-it-Like-One.html
index dece2f3a..a64297b7 100644
--- a/Your-Classifier-is-Secretly-an-Energy-Based-Model,-and-You-Should-Treat-it-Like-One.html
+++ b/Your-Classifier-is-Secretly-an-Energy-Based-Model,-and-You-Should-Treat-it-Like-One.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -303,9 +303,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/Zero-shot-Learning-by-Generating-Task-specific-Adapters.html b/Zero-shot-Learning-by-Generating-Task-specific-Adapters.html
index a690ce20..cae6fd51 100644
--- a/Zero-shot-Learning-by-Generating-Task-specific-Adapters.html
+++ b/Zero-shot-Learning-by-Generating-Task-specific-Adapters.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -308,9 +308,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/archieve.html b/archieve.html
index e2870e8f..8ac7d4f9 100644
--- a/archieve.html
+++ b/archieve.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -184,7 +184,7 @@ <h2 id="blog-posts">Blog Posts</h2>
 
 <ul>
   <li>
-    <p>07 Jan 2022 » <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design"> Hints for Computer System Design </a></p>
+    <p>10 Feb 2023 » <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools"> Toolformer - Language Models Can Teach Themselves to Use Tools </a></p>
   </li>
   <li>
     <p>29 Mar 2021 » <a href="https://shagunsodhani.github.io/papers-I-read/Synthesized-Policies-for-Transfer-and-Adaptation-across-Tasks-and-Environments"> Synthesized Policies for Transfer and Adaptation across Tasks and Environments </a></p>
diff --git a/atom.xml b/atom.xml
index ba94a61c..b199e018 100644
--- a/atom.xml
+++ b/atom.xml
@@ -4,7 +4,7 @@
  <title>Papers I Read</title>
  <link href="https://shagunsodhani.github.io/papers-I-read/atom.xml" rel="self"/>
  <link href="https://shagunsodhani.github.io/papers-I-read/"/>
- <updated>2022-02-01T22:09:12-05:00</updated>
+ <updated>2023-02-12T13:51:43-05:00</updated>
  <id>https://shagunsodhani.github.io/papers-I-read</id>
  <author>
    <name>Shagun Sodhani</name>
@@ -13,134 +13,230 @@
 
  
  <entry>
-   <title>Hints for Computer System Design</title>
-   <link href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design"/>
-   <updated>2022-01-07T00:00:00-05:00</updated>
-   <id>https://shagunsodhani.github.io/papers-I-read/Hints for Computer System Design</id>
-   <content type="html">&lt;ul&gt;
+   <title>Toolformer - Language Models Can Teach Themselves to Use Tools</title>
+   <link href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools"/>
+   <updated>2023-02-10T00:00:00-05:00</updated>
+   <id>https://shagunsodhani.github.io/papers-I-read/Toolformer - Language Models Can Teach Themselves to Use Tools</id>
+   <content type="html">&lt;h2 id=&quot;introduction&quot;&gt;Introduction&lt;/h2&gt;
+
+&lt;ul&gt;
   &lt;li&gt;
-    &lt;p&gt;The paper outlines some general hints for system design.&lt;/p&gt;
+    &lt;p&gt;The paper presents Toolformer, a language model that uses simple APIs to use external tools (calculator, QA system, search engine, translation system, and calendar).&lt;/p&gt;
   &lt;/li&gt;
   &lt;li&gt;
-    &lt;p&gt;&lt;a href=&quot;https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/acrobat-17.pdf&quot;&gt;Link to the paper&lt;/a&gt;&lt;/p&gt;
+    &lt;p&gt;&lt;a href=&quot;https://arxiv.org/abs/2302.04761&quot;&gt;Link to the paper&lt;/a&gt;&lt;/p&gt;
   &lt;/li&gt;
-  &lt;li&gt;
-    &lt;p&gt;Interface design&lt;/p&gt;
+&lt;/ul&gt;
 
-    &lt;ul&gt;
-      &lt;li&gt;
-        &lt;p&gt;Three conflicting requirements: Interface should be simple, complete, and admit a sufficiently small and fast implementation.&lt;/p&gt;
-      &lt;/li&gt;
-      &lt;li&gt;
-        &lt;p&gt;Difficulty: Each interface is a small programming language.&lt;/p&gt;
-      &lt;/li&gt;
-      &lt;li&gt;
-        &lt;p&gt;Hints&lt;/p&gt;
+&lt;h2 id=&quot;approach&quot;&gt;Approach&lt;/h2&gt;
 
-        &lt;ul&gt;
-          &lt;li&gt;
-            &lt;p&gt;Do one thing at a time and do it well.&lt;/p&gt;
-          &lt;/li&gt;
-          &lt;li&gt;
-            &lt;p&gt;Interface should not promise more than the implementor knows to deliver.&lt;/p&gt;
-          &lt;/li&gt;
-          &lt;li&gt;
-            &lt;p&gt;Make the program fast, rather than making it general or powerful.&lt;/p&gt;
-          &lt;/li&gt;
-          &lt;li&gt;
-            &lt;p&gt;Abstraction should conceal undesirable properties.&lt;/p&gt;
-          &lt;/li&gt;
-          &lt;li&gt;
-            &lt;p&gt;Keep basic interfaces stable.&lt;/p&gt;
-          &lt;/li&gt;
-        &lt;/ul&gt;
-      &lt;/li&gt;
-    &lt;/ul&gt;
+&lt;ul&gt;
+  &lt;li&gt;
+    &lt;p&gt;Starting with a language model, M, the goal is to enable the language model to use tools by invoking API calls.&lt;/p&gt;
+  &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;An API call is denoted by the tuple $c = (api_name, api_input)$. It can be linearized as $e(c) = [api_name(api_input)]$ or as $e(c, r) = [api_name(api_input) -&amp;gt; r]$ where $r$ denotes the result of the API.&lt;/p&gt;
+  &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;The given dataset of plain text, $C$, is converted into a dataset $C*$ augmented with the API calls using a three-step process.&lt;/p&gt;
   &lt;/li&gt;
   &lt;li&gt;
-    &lt;p&gt;Making implementations work&lt;/p&gt;
+    &lt;p&gt;In the first step, a position ($i$) and API call candidates (for the position $i$) are sampled.&lt;/p&gt;
 
     &lt;ul&gt;
       &lt;li&gt;
-        &lt;p&gt;Plan to throw away the first implementation.&lt;/p&gt;
+        &lt;p&gt;Positions are sampled by (i) computing the probability that M assigns to starting an API call for each position and (ii) retaining the top-$k$ positions with a probability greater than a threshold value.&lt;/p&gt;
       &lt;/li&gt;
       &lt;li&gt;
-        &lt;p&gt;Divide and conquer - reduce a hard problem to many easy ones.&lt;/p&gt;
-      &lt;/li&gt;
-      &lt;li&gt;
-        &lt;p&gt;Use a good idea again, instead of generalizing it. Sometimes, using a specialized implementation of the idea may be better than using a general one.&lt;/p&gt;
+        &lt;p&gt;For each of the sampled positions (say $i$), API calls are sampled by concatenating a prompt to the tokens till index $i$ and sampling from the model M. Examples that do not generate the “end of the API” token (i.e.,”]”) are discarded.&lt;/p&gt;
       &lt;/li&gt;
     &lt;/ul&gt;
   &lt;/li&gt;
   &lt;li&gt;
-    &lt;p&gt;Handling all the cases&lt;/p&gt;
+    &lt;p&gt;In the second step, the API calls are executed to obtain response $r$ (text sequence).&lt;/p&gt;
 
     &lt;ul&gt;
-      &lt;li&gt;Handle normal and worst cases separately as their requirements can differ.&lt;/li&gt;
+      &lt;li&gt;API calls are filtered using the following criteria: if providing M with both the input and the output of the API makes it easier for M to predict the future token, compared to not using the API call at all or just using the input to the API, then the API call is helpful for M, and the example should be retained.&lt;/li&gt;
     &lt;/ul&gt;
   &lt;/li&gt;
   &lt;li&gt;
-    &lt;p&gt;Speed&lt;/p&gt;
+    &lt;p&gt;In the last step, the remaining API calls are merged to obtain the augmented dataset $C*$ that is used for finetuning M.&lt;/p&gt;
+  &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;Note that $C*$ contains $C$, so M is finetuned on the original dataset and examples where a tool is helpful.&lt;/p&gt;
+  &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;During inference, the model is used for decoding in the usual way. Decoding is stopped when it produces the “-&amp;gt;” token, and the corresponding API is used to generate the response. The decoding process (using the model) resumes with the API output appended to the decoded text.&lt;/p&gt;
+  &lt;/li&gt;
+&lt;/ul&gt;
+
+&lt;h2 id=&quot;tools&quot;&gt;Tools&lt;/h2&gt;
+
+&lt;ul&gt;
+  &lt;li&gt;
+    &lt;p&gt;There are two constraints on the tools: (i) their input and output should be expressible as text, and (ii) few demonstrations can be obtained from the tools. The second constraint means that the tool should be useable or accessible.&lt;/p&gt;
+  &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;The paper considered the following tools: a question-answering system, a Wikipedia search engine, a calculator, a calendar, and a machine translation system. Of these, only the calculator and calendar are non-neural network tools.&lt;/p&gt;
+  &lt;/li&gt;
+&lt;/ul&gt;
+
+&lt;h2 id=&quot;experiments&quot;&gt;Experiments&lt;/h2&gt;
+
+&lt;ul&gt;
+  &lt;li&gt;
+    &lt;p&gt;Subset of CCNet is used as the language modeling dataset.&lt;/p&gt;
+  &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;GPT-J is used as the language model.&lt;/p&gt;
+  &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;For finetuning, the batch size is 128, the learning rate is 1e-5, and a linear warmup for the first 10% of training is used.&lt;/p&gt;
+  &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;Following models are compared:&lt;/p&gt;
 
     &lt;ul&gt;
       &lt;li&gt;
-        &lt;p&gt;Sometimes, it is better to split resources instead of sharing them.&lt;/p&gt;
-      &lt;/li&gt;
-      &lt;li&gt;
-        &lt;p&gt;Use static analysis.&lt;/p&gt;
-      &lt;/li&gt;
-      &lt;li&gt;
-        &lt;p&gt;Cache expensive computations.&lt;/p&gt;
+        &lt;p&gt;GPT-J: Regular GPT-J model without any finetuning.&lt;/p&gt;
       &lt;/li&gt;
       &lt;li&gt;
-        &lt;p&gt;Use “hints” to speed execution. A hint is like a cached value with two differences - the value may be wrong, and it may not be reachable by an associative lookup.&lt;/p&gt;
+        &lt;p&gt;GPT-J + CC: GPT-J finetuned on $C$ without any API calls.&lt;/p&gt;
       &lt;/li&gt;
       &lt;li&gt;
-        &lt;p&gt;When in doubt, use brute force.&lt;/p&gt;
+        &lt;p&gt;Toolformer, i.e. GPT-J finetuned on $C*$.&lt;/p&gt;
       &lt;/li&gt;
       &lt;li&gt;
-        &lt;p&gt;Whenever possible, compute in the background.&lt;/p&gt;
+        &lt;p&gt;Toolformer with API calls disabled during training.&lt;/p&gt;
       &lt;/li&gt;
       &lt;li&gt;
-        &lt;p&gt;Use batch processing.&lt;/p&gt;
+        &lt;p&gt;OPT 66B&lt;/p&gt;
       &lt;/li&gt;
       &lt;li&gt;
-        &lt;p&gt;When allocating resources, the first priority should be to avoid overloading the system (and not optimizing it).&lt;/p&gt;
+        &lt;p&gt;GPT-3&lt;/p&gt;
       &lt;/li&gt;
     &lt;/ul&gt;
   &lt;/li&gt;
   &lt;li&gt;
-    &lt;p&gt;Fault tolerance&lt;/p&gt;
+    &lt;p&gt;The models are evaluated in the prompted zero-shot setup, where models are instructed to solve a task without any in-context examples.&lt;/p&gt;
+  &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;One difference from the standard greedy decoding is that the API call is used whenever it is one of the top-10 most likely next tokens. This is done to increase the use of API calls.&lt;/p&gt;
+  &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;Evaluation Tasks&lt;/p&gt;
 
     &lt;ul&gt;
       &lt;li&gt;
-        &lt;p&gt;Retrofitting fault tolerance to an existing design is very hard.&lt;/p&gt;
+        &lt;p&gt;SQuAD, GoogleRE, and T-REx subsets of the LAMA benchmark where the model has to complete a short statement with a missing fact.&lt;/p&gt;
+
+        &lt;ul&gt;
+          &lt;li&gt;
+            &lt;p&gt;Since LAMA questions are based on Wikipedia, Toolformer isn’t allowed to use Wikipedia search.&lt;/p&gt;
+          &lt;/li&gt;
+          &lt;li&gt;
+            &lt;p&gt;The evaluation criteria is to check if the correct word is among the first five words predicted by the model.&lt;/p&gt;
+          &lt;/li&gt;
+          &lt;li&gt;
+            &lt;p&gt;Toolformer uses the question-answering tool for most cases, outperforming all the baselines.&lt;/p&gt;
+          &lt;/li&gt;
+        &lt;/ul&gt;
+      &lt;/li&gt;
+      &lt;li&gt;
+        &lt;p&gt;Math Dataset&lt;/p&gt;
+
+        &lt;ul&gt;
+          &lt;li&gt;
+            &lt;p&gt;eSDiv, SVAMP, and MAWPS benchmarks.&lt;/p&gt;
+          &lt;/li&gt;
+          &lt;li&gt;
+            &lt;p&gt;The first number predicted by the model is considered to be the output.&lt;/p&gt;
+          &lt;/li&gt;
+          &lt;li&gt;
+            &lt;p&gt;Toolformer uses the calculator tool for most cases, thereby outperforming all the baselines.&lt;/p&gt;
+          &lt;/li&gt;
+        &lt;/ul&gt;
       &lt;/li&gt;
       &lt;li&gt;
-        &lt;p&gt;Log updates to record the state of an object.&lt;/p&gt;
+        &lt;p&gt;Question Answering&lt;/p&gt;
+
+        &lt;ul&gt;
+          &lt;li&gt;
+            &lt;p&gt;Web Questions, Natural Questions, and TriviaQA datasets.&lt;/p&gt;
+          &lt;/li&gt;
+          &lt;li&gt;
+            &lt;p&gt;The evaluation criteria is to check if the correct word is among the first 20 words predicted by the model.&lt;/p&gt;
+          &lt;/li&gt;
+          &lt;li&gt;
+            &lt;p&gt;Question Answering tool is disabled for this setup.&lt;/p&gt;
+          &lt;/li&gt;
+          &lt;li&gt;
+            &lt;p&gt;Toolformer uses the Wikipedia tool for most cases, thereby outperforming all the baselines other than the much larger GPT-3 model.&lt;/p&gt;
+          &lt;/li&gt;
+        &lt;/ul&gt;
       &lt;/li&gt;
       &lt;li&gt;
-        &lt;p&gt;Each log entry should consist of the name of the update procedure and its arguments.&lt;/p&gt;
+        &lt;p&gt;Multilingual Question Answering&lt;/p&gt;
+
+        &lt;ul&gt;
+          &lt;li&gt;
+            &lt;p&gt;MLQA benchmark.&lt;/p&gt;
+          &lt;/li&gt;
+          &lt;li&gt;
+            &lt;p&gt;The evaluation criteria is to check if the correct word is among the first ten words predicted by the model.&lt;/p&gt;
+          &lt;/li&gt;
+          &lt;li&gt;
+            &lt;p&gt;Toolformer uses the translation tool for most of the questions, with questions in Hindi being an exception.&lt;/p&gt;
+          &lt;/li&gt;
+          &lt;li&gt;
+            &lt;p&gt;However, Toolformer does not consistently outperform the GPT-J baseline, likely because, for some languages, finetuning on CCNet could hurt performance.&lt;/p&gt;
+          &lt;/li&gt;
+        &lt;/ul&gt;
       &lt;/li&gt;
       &lt;li&gt;
-        &lt;p&gt;The procedure must be a stateless function, and the argument must be valued and not references to mutable objects.&lt;/p&gt;
+        &lt;p&gt;Temporal Datasets&lt;/p&gt;
+
+        &lt;ul&gt;
+          &lt;li&gt;
+            &lt;p&gt;TEMPLAMA (cloze style queries where the answer changes with time) and DATESET (dataset generated through a series of templates and populated with random dates/durations).&lt;/p&gt;
+          &lt;/li&gt;
+          &lt;li&gt;
+            &lt;p&gt;While Toolformer outperforms the baselines for both datasets, it relies on the Wikipedia search and Question Answering tools (and not the calendar tool) for the LAMA dataset. On the DATESET dataset, it uses the calendar tool in the majority.&lt;/p&gt;
+          &lt;/li&gt;
+        &lt;/ul&gt;
       &lt;/li&gt;
       &lt;li&gt;
-        &lt;p&gt;Make actions atomic or restartable&lt;/p&gt;
+        &lt;p&gt;Language Modeling&lt;/p&gt;
 
         &lt;ul&gt;
           &lt;li&gt;
-            &lt;p&gt;Atomic actions are either complete or have no effect. If an atomic action fails, there is no need to deal with the intermediate state/effect of the action.&lt;/p&gt;
+            &lt;p&gt;WikiText and a subset of 10,000 randomly selected documents from CCNet (not used during training of M).&lt;/p&gt;
           &lt;/li&gt;
           &lt;li&gt;
-            &lt;p&gt;A restartable action can be partially executed many times before a complete execution.&lt;/p&gt;
+            &lt;p&gt;Training on $C*$ does not increase perplexity (compared to training on C). In this experiment, the API calls are disabled during inference.&lt;/p&gt;
           &lt;/li&gt;
         &lt;/ul&gt;
       &lt;/li&gt;
     &lt;/ul&gt;
   &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;Varying the size of the underlying models show that the ability to use tools emerges only around 755M parameters.&lt;/p&gt;
+  &lt;/li&gt;
 &lt;/ul&gt;
 
+&lt;h2 id=&quot;future-work&quot;&gt;Future Work&lt;/h2&gt;
+
+&lt;ul&gt;
+  &lt;li&gt;
+    &lt;p&gt;Extending Toolformer to chain the use of tools and use tools interactively.&lt;/p&gt;
+  &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;In some cases, the use of tools is very sample-inefficient.&lt;/p&gt;
+  &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;Decision to use a tool does not account for the cost of using the tool.&lt;/p&gt;
+  &lt;/li&gt;
+&lt;/ul&gt;
 </content>
  </entry>
  
diff --git a/index.html b/index.html
index d0b7c29b..c1ae2d2e 100644
--- a/index.html
+++ b/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -182,20 +182,20 @@ <h3 class="masthead-title">
   
   <div class="post">
     <h1 class="post-title">
-      <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-        Hints for Computer System Design
+      <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+        Toolformer - Language Models Can Teach Themselves to Use Tools
       </a>
     </h1>
 
-    <span class="post-date">07 Jan 2022</span>
+    <span class="post-date">10 Feb 2023</span>
 
       <div class="excerpt">
-        <ul> <li> <p>The paper outlines some general hints for system design.</p> </li> <li> <p><a href="https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/acrobat-17.pdf">Link...
-        <!-- <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design"> Continue reading</a> -->
+        <h2 id="introduction">Introduction</h2> <ul> <li> <p>The paper presents Toolformer, a language model that uses simple APIs...
+        <!-- <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools"> Continue reading</a> -->
         <br>
 <!--         <span class="comments-count">
           <a class="comments-count-icon"><i class="fa fa-comment"></i></a>
-          <a href="/Hints-for-Computer-System-Design#disqus_thread"> Comments</a>
+          <a href="/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools#disqus_thread"> Comments</a>
         </span> -->
       </div>
   </div>
diff --git a/mixup-Beyond-Empirical-Risk-Minimization.html b/mixup-Beyond-Empirical-Risk-Minimization.html
index 375b3f20..dda891b8 100644
--- a/mixup-Beyond-Empirical-Risk-Minimization.html
+++ b/mixup-Beyond-Empirical-Risk-Minimization.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -262,9 +262,9 @@ <h2>Related Posts</h2>
     
       <li>
         <h3>
-          <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">
-            Hints for Computer System Design
-            <small>07 Jan 2022</small>
+          <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">
+            Toolformer - Language Models Can Teach Themselves to Use Tools
+            <small>10 Feb 2023</small>
           </a>
         </h3>
       </li>
diff --git a/page10/index.html b/page10/index.html
index 55cf5443..15e6468b 100644
--- a/page10/index.html
+++ b/page10/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/page11/index.html b/page11/index.html
index 32e2ad5e..8fd42a18 100644
--- a/page11/index.html
+++ b/page11/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/page12/index.html b/page12/index.html
index a5564f8a..dab75016 100644
--- a/page12/index.html
+++ b/page12/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/page13/index.html b/page13/index.html
index c3a79c41..1f2b9755 100644
--- a/page13/index.html
+++ b/page13/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/page14/index.html b/page14/index.html
index 45d7659d..61ca2717 100644
--- a/page14/index.html
+++ b/page14/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/page15/index.html b/page15/index.html
index 3ef8d7e2..387bed1d 100644
--- a/page15/index.html
+++ b/page15/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/page2/index.html b/page2/index.html
index 2216c2ba..9f43b4cf 100644
--- a/page2/index.html
+++ b/page2/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/page3/index.html b/page3/index.html
index f4e90d1e..454d1caa 100644
--- a/page3/index.html
+++ b/page3/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/page4/index.html b/page4/index.html
index 5a2f7bb2..7186672e 100644
--- a/page4/index.html
+++ b/page4/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/page5/index.html b/page5/index.html
index 7883865e..d7046818 100644
--- a/page5/index.html
+++ b/page5/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/page6/index.html b/page6/index.html
index cc95d24f..bb19b8d5 100644
--- a/page6/index.html
+++ b/page6/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/page7/index.html b/page7/index.html
index 8757b044..7642a2aa 100644
--- a/page7/index.html
+++ b/page7/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/page8/index.html b/page8/index.html
index 708b6612..7f504b17 100644
--- a/page8/index.html
+++ b/page8/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/page9/index.html b/page9/index.html
index 25b18047..49f665dc 100644
--- a/page9/index.html
+++ b/page9/index.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
diff --git a/tags.html b/tags.html
index 89426779..57947cbb 100644
--- a/tags.html
+++ b/tags.html
@@ -159,7 +159,7 @@
 
   <div class="sidebar-item">
     <p>
-      &copy; 2022. All rights reserved.
+      &copy; 2023. All rights reserved.
     </p>
   </div>
 </div>
@@ -181,15 +181,13 @@ <h3 class="masthead-title">
         <h1 class="page-title">Tags</h1>
 	<a href="https://shagunsodhani.github.io/papers-I-read/tags"></a> 
   
-<!-- site_tags: 2015,ICCV 2015,AI,CV,Dataset,ICCV,NLP,VQA,CVPR,Embedding,CVPR 2017,2017,2016,CVPR 2016,Neural Module Network,2014,EMNLP 2014,Dependency Parsing,EMNLP,EMNLP 2016,Attention,Natural Language Inference,SOTA,ACL 2015,ACL,Word Vectors,Multi Modal,Multi Model,Speech,POS,QA,Sentiment Analysis,Out of Distribution,Softmax,KDD 2017,KDD,Machine Comprehension,RL,Out of Vocabulary Words,NIPS 2015,Seq2Seq,NIPS,Relational Network,Representation Learning,NMT,EMNLP 2017,Information Retrieval,ACL 2017,Activation Function,Self Gated,Graph Representation,Graph,ICLR 2015,ICLR,2002,Science 2002,Motif,Network,Science,Science 2016,Clustering,Transfer Learning,ICML 2016,ICML,KDD 2015,Network Embedding,NIPS 2014,Conversational Agent,Multi Task,Abstract Summarization,Pointer Network,Summarization,ACL 2016,NLG,Workshop,2018,Dynamical System,Latent Variable,Relational Inference,GNN,VAE,Graph Neural Network,SAT,Catastrophic Forgetting,ICLR 2014,Activation,Accelerated Training,Learning Rate,WACV 2017,LR,WACV,Pruning Network,Hypothesis,Initialization,Unsupervised,Message Passing,Neural Message Passing,Chemistry,MPNN,Count Based VQA,ICLR 2018,ICLR 2016,Knowledge Transfer,Lifelong Learning,ICML 2018,Knowledge Distillation,KD,Continual Learning,Incremental Learning,Weight Adaptation,Causal Learning,Causality,Recurrent Neural Network,Kronecker,KRU,RNN,NIPS 2017,Model-Based,Model-Free,Pooling,Loss Function,Semantic Loss,Symbolic Knowledge,Loss,AAAI 2018,Emergent Language,Multi-Agent,Natural Language Processing,AAAI,NIPS Workskop,Virtual Embodiment,Theory,Hyperbolic Embedding,Poincare Ball Model,Tree,Curriculum Learning,Grounded Language Learning,Interactive Teaching,Reinforcement Learning,Environment,Memory Augmented Neural Network,Meta Learning,One shot learning,MANN,Memory,ICML 2017,Hierarchial RNN,Learning Optimizer',Optimizer,Hyperboloid Model,Off policy RL,Sample Efficient,Kernel,Pretraining,2019,ICLR 2019,CL,Hierarchical RL,Mujoco,Modular Meta Learning,Modular ML,Modular Network,Module,Information Theory,Entropy,Linear Algebra,Linear Model,Matrix Factorization,Tucker Decomposition,Factorization,Matrix,AAMAS 2019,Hierarchical Reinforcement Learning,AAMAS,HRL,Empirical Advice,NeurIPS 2018,NeurIPS Workshop 2018,Neural Computation,Neural Computation 2002,Data Augmentation,Sequential models,Compositionality,Deep Reinforcement Learning,Relational Learning,RRL,Meta Reinforcement Learning,Structured Exploration,Exploration,NeurIPS,ICML 2019,Inverse Reinforcement Learning,IRL,Physics,Relation Learning,Set,Evaluating Generalization,DRL,Evaluation,Generalization,Neurips 2018,Neurips,Abductive Reasoning,NLI,Reasoning,Key Value,Physical Reasoning,Benchmark,MAML,Distributed Reinforcement Learning,Neurips 2019,Object-Oriented Learning,Planning,EMNLP 2019,Procedural Text,Transformer,2006,Markov Decision Process,State Abstraction,MDP,LL,Distributed Computing,Distributed SGD,Synchronous SGD,ImageNet,ICLR 2020,Multi Domain,Neural Machine Translation,Scale,Adversarial Robustness,Energy-Based Models,Generative Models,Hybrid Models,Outlier Detection,Out of Distribution Detection,Adversarial,Calibration,EBM,Robustness,NeurIPS 2019,Replay Buffer,Finetuning,ICLR 2018',ERM,2010,ECCV 2010,ECCV,2020,Contrastive Learning,Self Supervised,Contrastive,Online Learning,Empirical,Credit Assignment,Decentralized Reinforcement Learning,ICML 2020,Economics,Stochastic Gradient Descent,UAI 2018,SGD,SWA,UAI,Batch Normalisation,ICML 2020',BatchNorm,BN,Normalization,Gradient Manipulation,Gradient Normalization,Conditional Computation,ICLR 2017,Mixture of Experts,Gating,Long-tailed Dataset,Classifier,1999,Distributed Systems,Operating Systems,CAP,OS,Geometry,Invariance,NeurIPS 2020,2012,Build System,Software Engineering,Technical Debt,Engineering,IEEE,Software,Systems,Big Data,Data,Database,DBMS,SSO,USENIX,Siamese,SSL,Latency,ACID,BASE,Apache,Design Pattern,Container,Explainability,Interpretability,Model Parallelism,HyperNetwork,2021,Text-to-Text Transformer,Zero-Shot,Zero Shot Generalization,Adapter,ICLR 2021,Representation Analysis,2013,Click-Through Rate,Data Mining,KDD 2013,Machine Learning,Ads,CTR,ML,KDD 2014,ACM,Recommender Systems,Ranking,Recommender,Generalizatio,1983 -->
+<!-- site_tags: 2015,ICCV 2015,AI,CV,Dataset,ICCV,NLP,VQA,CVPR,Embedding,CVPR 2017,2017,2016,CVPR 2016,Neural Module Network,2014,EMNLP 2014,Dependency Parsing,EMNLP,EMNLP 2016,Attention,Natural Language Inference,SOTA,ACL 2015,ACL,Word Vectors,Multi Modal,Multi Model,Speech,POS,QA,Sentiment Analysis,Out of Distribution,Softmax,KDD 2017,KDD,Machine Comprehension,RL,Out of Vocabulary Words,NIPS 2015,Seq2Seq,NIPS,Relational Network,Representation Learning,NMT,EMNLP 2017,Information Retrieval,ACL 2017,Activation Function,Self Gated,Graph Representation,Graph,ICLR 2015,ICLR,2002,Science 2002,Motif,Network,Science,Science 2016,Clustering,Transfer Learning,ICML 2016,ICML,KDD 2015,Network Embedding,NIPS 2014,Conversational Agent,Multi Task,Abstract Summarization,Pointer Network,Summarization,ACL 2016,NLG,Workshop,2018,Dynamical System,Latent Variable,Relational Inference,GNN,VAE,Graph Neural Network,SAT,Catastrophic Forgetting,ICLR 2014,Activation,Accelerated Training,Learning Rate,WACV 2017,LR,WACV,Pruning Network,Hypothesis,Initialization,Unsupervised,Message Passing,Neural Message Passing,Chemistry,MPNN,Count Based VQA,ICLR 2018,ICLR 2016,Knowledge Transfer,Lifelong Learning,ICML 2018,Knowledge Distillation,KD,Continual Learning,Incremental Learning,Weight Adaptation,Causal Learning,Causality,Recurrent Neural Network,Kronecker,KRU,RNN,NIPS 2017,Model-Based,Model-Free,Pooling,Loss Function,Semantic Loss,Symbolic Knowledge,Loss,AAAI 2018,Emergent Language,Multi-Agent,Natural Language Processing,AAAI,NIPS Workskop,Virtual Embodiment,Theory,Hyperbolic Embedding,Poincare Ball Model,Tree,Curriculum Learning,Grounded Language Learning,Interactive Teaching,Reinforcement Learning,Environment,Memory Augmented Neural Network,Meta Learning,One shot learning,MANN,Memory,ICML 2017,Hierarchial RNN,Learning Optimizer',Optimizer,Hyperboloid Model,Off policy RL,Sample Efficient,Kernel,Pretraining,2019,ICLR 2019,CL,Hierarchical RL,Mujoco,Modular Meta Learning,Modular ML,Modular Network,Module,Information Theory,Entropy,Linear Algebra,Linear Model,Matrix Factorization,Tucker Decomposition,Factorization,Matrix,AAMAS 2019,Hierarchical Reinforcement Learning,AAMAS,HRL,Empirical Advice,NeurIPS 2018,NeurIPS Workshop 2018,Neural Computation,Neural Computation 2002,Data Augmentation,Sequential models,Compositionality,Deep Reinforcement Learning,Relational Learning,RRL,Meta Reinforcement Learning,Structured Exploration,Exploration,NeurIPS,ICML 2019,Inverse Reinforcement Learning,IRL,Physics,Relation Learning,Set,Evaluating Generalization,DRL,Evaluation,Generalization,Neurips 2018,Neurips,Abductive Reasoning,NLI,Reasoning,Key Value,Physical Reasoning,Benchmark,MAML,Distributed Reinforcement Learning,Neurips 2019,Object-Oriented Learning,Planning,EMNLP 2019,Procedural Text,Transformer,2006,Markov Decision Process,State Abstraction,MDP,LL,Distributed Computing,Distributed SGD,Synchronous SGD,ImageNet,ICLR 2020,Multi Domain,Neural Machine Translation,Scale,Adversarial Robustness,Energy-Based Models,Generative Models,Hybrid Models,Outlier Detection,Out of Distribution Detection,Adversarial,Calibration,EBM,Robustness,NeurIPS 2019,Replay Buffer,Finetuning,ICLR 2018',ERM,2010,ECCV 2010,ECCV,2020,Contrastive Learning,Self Supervised,Contrastive,Online Learning,Empirical,Credit Assignment,Decentralized Reinforcement Learning,ICML 2020,Economics,Stochastic Gradient Descent,UAI 2018,SGD,SWA,UAI,Batch Normalisation,ICML 2020',BatchNorm,BN,Normalization,Gradient Manipulation,Gradient Normalization,Conditional Computation,ICLR 2017,Mixture of Experts,Gating,Long-tailed Dataset,Classifier,1999,Distributed Systems,Operating Systems,CAP,OS,Geometry,Invariance,NeurIPS 2020,2012,Build System,Software Engineering,Technical Debt,Engineering,IEEE,Software,Systems,Big Data,Data,Database,DBMS,SSO,USENIX,Siamese,SSL,Latency,ACID,BASE,Apache,Design Pattern,Container,Explainability,Interpretability,Model Parallelism,HyperNetwork,2021,Text-to-Text Transformer,Zero-Shot,Zero Shot Generalization,Adapter,ICLR 2021,Representation Analysis,2013,Click-Through Rate,Data Mining,KDD 2013,Machine Learning,Ads,CTR,ML,KDD 2014,ACM,Recommender Systems,Ranking,Recommender,Generalizatio,2023,Large Language Model,PreTrained Langauge Model,GPT,LLM,OPT -->
 
-<!-- tag_words: 198319992002200620102012201320142015201620172018201920202021AAAIAAAI 2018AAMASAAMAS 2019ACIDACLACL 2015ACL 2016ACL 2017ACMAIAbductive ReasoningAbstract SummarizationAccelerated TrainingActivationActivation FunctionAdapterAdsAdversarialAdversarial RobustnessApacheAttentionBASEBNBatch NormalisationBatchNormBenchmarkBig DataBuild SystemCAPCLCTRCVCVPRCVPR 2016CVPR 2017CalibrationCatastrophic ForgettingCausal LearningCausalityChemistryClassifierClick-Through RateClusteringCompositionalityConditional ComputationContainerContinual LearningContrastiveContrastive LearningConversational AgentCount Based VQACredit AssignmentCurriculum LearningDBMSDRLDataData AugmentationData MiningDatabaseDatasetDecentralized Reinforcement LearningDeep Reinforcement LearningDependency ParsingDesign PatternDistributed ComputingDistributed Reinforcement LearningDistributed SGDDistributed SystemsDynamical SystemEBMECCVECCV 2010EMNLPEMNLP 2014EMNLP 2016EMNLP 2017EMNLP 2019ERMEconomicsEmbeddingEmergent LanguageEmpiricalEmpirical AdviceEnergy-Based ModelsEngineeringEntropyEnvironmentEvaluating GeneralizationEvaluationExplainabilityExplorationFactorizationFinetuningGNNGatingGeneralizatioGeneralizationGenerative ModelsGeometryGradient ManipulationGradient NormalizationGraphGraph Neural NetworkGraph RepresentationGrounded Language LearningHRLHierarchial RNNHierarchical RLHierarchical Reinforcement LearningHybrid ModelsHyperNetworkHyperbolic EmbeddingHyperboloid ModelHypothesisICCVICCV 2015ICLRICLR 2014ICLR 2015ICLR 2016ICLR 2017ICLR 2018ICLR 2018'ICLR 2019ICLR 2020ICLR 2021ICMLICML 2016ICML 2017ICML 2018ICML 2019ICML 2020ICML 2020'IEEEIRLImageNetIncremental LearningInformation RetrievalInformation TheoryInitializationInteractive TeachingInterpretabilityInvarianceInverse Reinforcement LearningKDKDDKDD 2013KDD 2014KDD 2015KDD 2017KRUKernelKey ValueKnowledge DistillationKnowledge TransferKroneckerLLLRLatencyLatent VariableLearning Optimizer'Learning RateLifelong LearningLinear AlgebraLinear ModelLong-tailed DatasetLossLoss FunctionMAMLMANNMDPMLMPNNMachine ComprehensionMachine LearningMarkov Decision ProcessMatrixMatrix FactorizationMemoryMemory Augmented Neural NetworkMessage PassingMeta LearningMeta Reinforcement LearningMixture of ExpertsModel ParallelismModel-BasedModel-FreeModular MLModular Meta LearningModular NetworkModuleMotifMujocoMulti DomainMulti ModalMulti ModelMulti TaskMulti-AgentNIPSNIPS 2014NIPS 2015NIPS 2017NIPS WorkskopNLGNLINLPNMTNatural Language InferenceNatural Language ProcessingNetworkNetwork EmbeddingNeurIPSNeurIPS 2018NeurIPS 2019NeurIPS 2020NeurIPS Workshop 2018Neural ComputationNeural Computation 2002Neural Machine TranslationNeural Message PassingNeural Module NetworkNeuripsNeurips 2018Neurips 2019NormalizationOSObject-Oriented LearningOff policy RLOne shot learningOnline LearningOperating SystemsOptimizerOut of DistributionOut of Distribution DetectionOut of Vocabulary WordsOutlier DetectionPOSPhysical ReasoningPhysicsPlanningPoincare Ball ModelPointer NetworkPoolingPretrainingProcedural TextPruning NetworkQARLRNNRRLRankingReasoningRecommenderRecommender SystemsRecurrent Neural NetworkReinforcement LearningRelation LearningRelational InferenceRelational LearningRelational NetworkReplay BufferRepresentation AnalysisRepresentation LearningRobustnessSATSGDSOTASSLSSOSWASample EfficientScaleScienceScience 2002Science 2016Self GatedSelf SupervisedSemantic LossSentiment AnalysisSeq2SeqSequential modelsSetSiameseSoftmaxSoftwareSoftware EngineeringSpeechState AbstractionStochastic Gradient DescentStructured ExplorationSummarizationSymbolic KnowledgeSynchronous SGDSystemsTechnical DebtText-to-Text TransformerTheoryTransfer LearningTransformerTreeTucker DecompositionUAIUAI 2018USENIXUnsupervisedVAEVQAVirtual EmbodimentWACVWACV 2017Weight AdaptationWord VectorsWorkshopZero Shot GeneralizationZero-Shot -->
+<!-- tag_words: 199920022006201020122013201420152016201720182019202020212023AAAIAAAI 2018AAMASAAMAS 2019ACIDACLACL 2015ACL 2016ACL 2017ACMAIAbductive ReasoningAbstract SummarizationAccelerated TrainingActivationActivation FunctionAdapterAdsAdversarialAdversarial RobustnessApacheAttentionBASEBNBatch NormalisationBatchNormBenchmarkBig DataBuild SystemCAPCLCTRCVCVPRCVPR 2016CVPR 2017CalibrationCatastrophic ForgettingCausal LearningCausalityChemistryClassifierClick-Through RateClusteringCompositionalityConditional ComputationContainerContinual LearningContrastiveContrastive LearningConversational AgentCount Based VQACredit AssignmentCurriculum LearningDBMSDRLDataData AugmentationData MiningDatabaseDatasetDecentralized Reinforcement LearningDeep Reinforcement LearningDependency ParsingDesign PatternDistributed ComputingDistributed Reinforcement LearningDistributed SGDDistributed SystemsDynamical SystemEBMECCVECCV 2010EMNLPEMNLP 2014EMNLP 2016EMNLP 2017EMNLP 2019ERMEconomicsEmbeddingEmergent LanguageEmpiricalEmpirical AdviceEnergy-Based ModelsEngineeringEntropyEnvironmentEvaluating GeneralizationEvaluationExplainabilityExplorationFactorizationFinetuningGNNGPTGatingGeneralizatioGeneralizationGenerative ModelsGeometryGradient ManipulationGradient NormalizationGraphGraph Neural NetworkGraph RepresentationGrounded Language LearningHRLHierarchial RNNHierarchical RLHierarchical Reinforcement LearningHybrid ModelsHyperNetworkHyperbolic EmbeddingHyperboloid ModelHypothesisICCVICCV 2015ICLRICLR 2014ICLR 2015ICLR 2016ICLR 2017ICLR 2018ICLR 2018'ICLR 2019ICLR 2020ICLR 2021ICMLICML 2016ICML 2017ICML 2018ICML 2019ICML 2020ICML 2020'IEEEIRLImageNetIncremental LearningInformation RetrievalInformation TheoryInitializationInteractive TeachingInterpretabilityInvarianceInverse Reinforcement LearningKDKDDKDD 2013KDD 2014KDD 2015KDD 2017KRUKernelKey ValueKnowledge DistillationKnowledge TransferKroneckerLLLLMLRLarge Language ModelLatencyLatent VariableLearning Optimizer'Learning RateLifelong LearningLinear AlgebraLinear ModelLong-tailed DatasetLossLoss FunctionMAMLMANNMDPMLMPNNMachine ComprehensionMachine LearningMarkov Decision ProcessMatrixMatrix FactorizationMemoryMemory Augmented Neural NetworkMessage PassingMeta LearningMeta Reinforcement LearningMixture of ExpertsModel ParallelismModel-BasedModel-FreeModular MLModular Meta LearningModular NetworkModuleMotifMujocoMulti DomainMulti ModalMulti ModelMulti TaskMulti-AgentNIPSNIPS 2014NIPS 2015NIPS 2017NIPS WorkskopNLGNLINLPNMTNatural Language InferenceNatural Language ProcessingNetworkNetwork EmbeddingNeurIPSNeurIPS 2018NeurIPS 2019NeurIPS 2020NeurIPS Workshop 2018Neural ComputationNeural Computation 2002Neural Machine TranslationNeural Message PassingNeural Module NetworkNeuripsNeurips 2018Neurips 2019NormalizationOPTOSObject-Oriented LearningOff policy RLOne shot learningOnline LearningOperating SystemsOptimizerOut of DistributionOut of Distribution DetectionOut of Vocabulary WordsOutlier DetectionPOSPhysical ReasoningPhysicsPlanningPoincare Ball ModelPointer NetworkPoolingPreTrained Langauge ModelPretrainingProcedural TextPruning NetworkQARLRNNRRLRankingReasoningRecommenderRecommender SystemsRecurrent Neural NetworkReinforcement LearningRelation LearningRelational InferenceRelational LearningRelational NetworkReplay BufferRepresentation AnalysisRepresentation LearningRobustnessSATSGDSOTASSLSSOSWASample EfficientScaleScienceScience 2002Science 2016Self GatedSelf SupervisedSemantic LossSentiment AnalysisSeq2SeqSequential modelsSetSiameseSoftmaxSoftwareSoftware EngineeringSpeechState AbstractionStochastic Gradient DescentStructured ExplorationSummarizationSymbolic KnowledgeSynchronous SGDSystemsTechnical DebtText-to-Text TransformerTheoryTransfer LearningTransformerTreeTucker DecompositionUAIUAI 2018USENIXUnsupervisedVAEVQAVirtual EmbodimentWACVWACV 2017Weight AdaptationWord VectorsWorkshopZero Shot GeneralizationZero-Shot -->
 
 <div id="tags">
   <ul class="tag-box inline">
   
-    <li><a href="#1983">1983 <span>1</span></a></li>
-  
     <li><a href="#1999">1999 <span>1</span></a></li>
   
     <li><a href="#2002">2002 <span>2</span></a></li>
@@ -218,6 +216,8 @@ <h1 class="page-title">Tags</h1>
   
     <li><a href="#2021">2021 <span>1</span></a></li>
   
+    <li><a href="#2023">2023 <span>1</span></a></li>
+  
     <li><a href="#AAAI">AAAI <span>1</span></a></li>
   
     <li><a href="#AAAI+2018">AAAI 2018 <span>1</span></a></li>
@@ -238,7 +238,7 @@ <h1 class="page-title">Tags</h1>
   
     <li><a href="#ACM">ACM <span>2</span></a></li>
   
-    <li><a href="#AI">AI <span>126</span></a></li>
+    <li><a href="#AI">AI <span>127</span></a></li>
   
     <li><a href="#Abductive+Reasoning">Abductive Reasoning <span>1</span></a></li>
   
@@ -346,7 +346,7 @@ <h1 class="page-title">Tags</h1>
   
     <li><a href="#Dependency+Parsing">Dependency Parsing <span>1</span></a></li>
   
-    <li><a href="#Design+Pattern">Design Pattern <span>2</span></a></li>
+    <li><a href="#Design+Pattern">Design Pattern <span>1</span></a></li>
   
     <li><a href="#Distributed+Computing">Distributed Computing <span>3</span></a></li>
   
@@ -388,7 +388,7 @@ <h1 class="page-title">Tags</h1>
   
     <li><a href="#Energy-Based+Models">Energy-Based Models <span>2</span></a></li>
   
-    <li><a href="#Engineering">Engineering <span>12</span></a></li>
+    <li><a href="#Engineering">Engineering <span>11</span></a></li>
   
     <li><a href="#Entropy">Entropy <span>1</span></a></li>
   
@@ -408,6 +408,8 @@ <h1 class="page-title">Tags</h1>
   
     <li><a href="#GNN">GNN <span>6</span></a></li>
   
+    <li><a href="#GPT">GPT <span>1</span></a></li>
+  
     <li><a href="#Gating">Gating <span>1</span></a></li>
   
     <li><a href="#Generalizatio">Generalizatio <span>1</span></a></li>
@@ -534,8 +536,12 @@ <h1 class="page-title">Tags</h1>
   
     <li><a href="#LL">LL <span>6</span></a></li>
   
+    <li><a href="#LLM">LLM <span>1</span></a></li>
+  
     <li><a href="#LR">LR <span>1</span></a></li>
   
+    <li><a href="#Large+Language+Model">Large Language Model <span>1</span></a></li>
+  
     <li><a href="#Latency">Latency <span>4</span></a></li>
   
     <li><a href="#Latent+Variable">Latent Variable <span>2</span></a></li>
@@ -670,6 +676,8 @@ <h1 class="page-title">Tags</h1>
   
     <li><a href="#Normalization">Normalization <span>1</span></a></li>
   
+    <li><a href="#OPT">OPT <span>1</span></a></li>
+  
     <li><a href="#OS">OS <span>1</span></a></li>
   
     <li><a href="#Object-Oriented+Learning">Object-Oriented Learning <span>2</span></a></li>
@@ -680,7 +688,7 @@ <h1 class="page-title">Tags</h1>
   
     <li><a href="#Online+Learning">Online Learning <span>1</span></a></li>
   
-    <li><a href="#Operating+Systems">Operating Systems <span>2</span></a></li>
+    <li><a href="#Operating+Systems">Operating Systems <span>1</span></a></li>
   
     <li><a href="#Optimizer">Optimizer <span>1</span></a></li>
   
@@ -706,6 +714,8 @@ <h1 class="page-title">Tags</h1>
   
     <li><a href="#Pooling">Pooling <span>1</span></a></li>
   
+    <li><a href="#PreTrained+Langauge+Model">PreTrained Langauge Model <span>1</span></a></li>
+  
     <li><a href="#Pretraining">Pretraining <span>2</span></a></li>
   
     <li><a href="#Procedural+Text">Procedural Text <span>1</span></a></li>
@@ -788,9 +798,9 @@ <h1 class="page-title">Tags</h1>
   
     <li><a href="#Softmax">Softmax <span>2</span></a></li>
   
-    <li><a href="#Software">Software <span>5</span></a></li>
+    <li><a href="#Software">Software <span>4</span></a></li>
   
-    <li><a href="#Software+Engineering">Software Engineering <span>6</span></a></li>
+    <li><a href="#Software+Engineering">Software Engineering <span>5</span></a></li>
   
     <li><a href="#Speech">Speech <span>1</span></a></li>
   
@@ -806,7 +816,7 @@ <h1 class="page-title">Tags</h1>
   
     <li><a href="#Synchronous+SGD">Synchronous SGD <span>1</span></a></li>
   
-    <li><a href="#Systems">Systems <span>12</span></a></li>
+    <li><a href="#Systems">Systems <span>11</span></a></li>
   
     <li><a href="#Technical+Debt">Technical Debt <span>1</span></a></li>
   
@@ -854,14 +864,6 @@ <h1 class="page-title">Tags</h1>
 
   
     
-  <h2 id="1983">1983</h2>
-  <ul class="posts">
-    
-    <li itemscope=""><span class="entry-date"><time datetime="2022-01-07T00:00:00-05:00" itemprop="datePublished">January 07, 2022</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">Hints for Computer System Design</a></li>
-    
-  </ul>
-  
-    
   <h2 id="1999">1999</h2>
   <ul class="posts">
     
@@ -1234,6 +1236,14 @@ <h2 id="2021">2021</h2>
   </ul>
   
     
+  <h2 id="2023">2023</h2>
+  <ul class="posts">
+    
+    <li itemscope=""><span class="entry-date"><time datetime="2023-02-10T00:00:00-05:00" itemprop="datePublished">February 10, 2023</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">Toolformer - Language Models Can Teach Themselves to Use Tools</a></li>
+    
+  </ul>
+  
+    
   <h2 id="AAAI">AAAI</h2>
   <ul class="posts">
     
@@ -1327,6 +1337,8 @@ <h2 id="ACM">ACM</h2>
   <h2 id="AI">AI</h2>
   <ul class="posts">
     
+    <li itemscope=""><span class="entry-date"><time datetime="2023-02-10T00:00:00-05:00" itemprop="datePublished">February 10, 2023</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">Toolformer - Language Models Can Teach Themselves to Use Tools</a></li>
+    
     <li itemscope=""><span class="entry-date"><time datetime="2021-03-29T00:00:00-04:00" itemprop="datePublished">March 29, 2021</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Synthesized-Policies-for-Transfer-and-Adaptation-across-Tasks-and-Environments">Synthesized Policies for Transfer and Adaptation across Tasks and Environments</a></li>
     
     <li itemscope=""><span class="entry-date"><time datetime="2021-02-22T00:00:00-05:00" itemprop="datePublished">February 22, 2021</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Anatomy-of-Catastrophic-Forgetting-Hidden-Representations-and-Task-Semantics">Anatomy of Catastrophic Forgetting - Hidden Representations and Task Semantics</a></li>
@@ -2219,8 +2231,6 @@ <h2 id="Dependency+Parsing">Dependency Parsing</h2>
   <h2 id="Design+Pattern">Design Pattern</h2>
   <ul class="posts">
     
-    <li itemscope=""><span class="entry-date"><time datetime="2022-01-07T00:00:00-05:00" itemprop="datePublished">January 07, 2022</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">Hints for Computer System Design</a></li>
-    
     <li itemscope=""><span class="entry-date"><time datetime="2020-12-21T00:00:00-05:00" itemprop="datePublished">December 21, 2020</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Design-patterns-for-container-based-distributed-systems">Design patterns for container-based distributed systems</a></li>
     
   </ul>
@@ -2461,8 +2471,6 @@ <h2 id="Energy-Based+Models">Energy-Based Models</h2>
   <h2 id="Engineering">Engineering</h2>
   <ul class="posts">
     
-    <li itemscope=""><span class="entry-date"><time datetime="2022-01-07T00:00:00-05:00" itemprop="datePublished">January 07, 2022</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">Hints for Computer System Design</a></li>
-    
     <li itemscope=""><span class="entry-date"><time datetime="2021-03-22T00:00:00-04:00" itemprop="datePublished">March 22, 2021</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Deep-Neural-Networks-for-YouTube-Recommendations">Deep Neural Networks for YouTube Recommendations</a></li>
     
     <li itemscope=""><span class="entry-date"><time datetime="2021-03-15T00:00:00-04:00" itemprop="datePublished">March 15, 2021</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/The-Tail-at-Scale">The Tail at Scale</a></li>
@@ -2580,6 +2588,14 @@ <h2 id="GNN">GNN</h2>
   </ul>
   
     
+  <h2 id="GPT">GPT</h2>
+  <ul class="posts">
+    
+    <li itemscope=""><span class="entry-date"><time datetime="2023-02-10T00:00:00-05:00" itemprop="datePublished">February 10, 2023</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">Toolformer - Language Models Can Teach Themselves to Use Tools</a></li>
+    
+  </ul>
+  
+    
   <h2 id="Gating">Gating</h2>
   <ul class="posts">
     
@@ -3328,6 +3344,14 @@ <h2 id="LL">LL</h2>
   </ul>
   
     
+  <h2 id="LLM">LLM</h2>
+  <ul class="posts">
+    
+    <li itemscope=""><span class="entry-date"><time datetime="2023-02-10T00:00:00-05:00" itemprop="datePublished">February 10, 2023</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">Toolformer - Language Models Can Teach Themselves to Use Tools</a></li>
+    
+  </ul>
+  
+    
   <h2 id="LR">LR</h2>
   <ul class="posts">
     
@@ -3336,6 +3360,14 @@ <h2 id="LR">LR</h2>
   </ul>
   
     
+  <h2 id="Large+Language+Model">Large Language Model</h2>
+  <ul class="posts">
+    
+    <li itemscope=""><span class="entry-date"><time datetime="2023-02-10T00:00:00-05:00" itemprop="datePublished">February 10, 2023</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">Toolformer - Language Models Can Teach Themselves to Use Tools</a></li>
+    
+  </ul>
+  
+    
   <h2 id="Latency">Latency</h2>
   <ul class="posts">
     
@@ -4124,6 +4156,14 @@ <h2 id="Normalization">Normalization</h2>
   </ul>
   
     
+  <h2 id="OPT">OPT</h2>
+  <ul class="posts">
+    
+    <li itemscope=""><span class="entry-date"><time datetime="2023-02-10T00:00:00-05:00" itemprop="datePublished">February 10, 2023</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">Toolformer - Language Models Can Teach Themselves to Use Tools</a></li>
+    
+  </ul>
+  
+    
   <h2 id="OS">OS</h2>
   <ul class="posts">
     
@@ -4173,8 +4213,6 @@ <h2 id="Online+Learning">Online Learning</h2>
   <h2 id="Operating+Systems">Operating Systems</h2>
   <ul class="posts">
     
-    <li itemscope=""><span class="entry-date"><time datetime="2022-01-07T00:00:00-05:00" itemprop="datePublished">January 07, 2022</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">Hints for Computer System Design</a></li>
-    
     <li itemscope=""><span class="entry-date"><time datetime="2020-09-21T00:00:00-04:00" itemprop="datePublished">September 21, 2020</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Harvest,-Yield,-and-Scalable-Tolerant-Systems">Harvest, Yield, and Scalable Tolerant Systems</a></li>
     
   </ul>
@@ -4284,6 +4322,14 @@ <h2 id="Pooling">Pooling</h2>
   </ul>
   
     
+  <h2 id="PreTrained+Langauge+Model">PreTrained Langauge Model</h2>
+  <ul class="posts">
+    
+    <li itemscope=""><span class="entry-date"><time datetime="2023-02-10T00:00:00-05:00" itemprop="datePublished">February 10, 2023</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Toolformer-Language-Models-Can-Teach-Themselves-to-Use-Tools">Toolformer - Language Models Can Teach Themselves to Use Tools</a></li>
+    
+  </ul>
+  
+    
   <h2 id="Pretraining">Pretraining</h2>
   <ul class="posts">
     
@@ -4815,8 +4861,6 @@ <h2 id="Softmax">Softmax</h2>
   <h2 id="Software">Software</h2>
   <ul class="posts">
     
-    <li itemscope=""><span class="entry-date"><time datetime="2022-01-07T00:00:00-05:00" itemprop="datePublished">January 07, 2022</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">Hints for Computer System Design</a></li>
-    
     <li itemscope=""><span class="entry-date"><time datetime="2020-12-14T00:00:00-05:00" itemprop="datePublished">December 14, 2020</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Cassandra-a-decentralized-structured-storage-system">Cassandra - a decentralized structured storage system</a></li>
     
     <li itemscope=""><span class="entry-date"><time datetime="2020-11-30T00:00:00-05:00" itemprop="datePublished">November 30, 2020</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Consistency-Tradeoffs-in-Modern-Distributed-Database-System-Design">Consistency Tradeoffs in Modern Distributed Database System Design</a></li>
@@ -4831,8 +4875,6 @@ <h2 id="Software">Software</h2>
   <h2 id="Software+Engineering">Software Engineering</h2>
   <ul class="posts">
     
-    <li itemscope=""><span class="entry-date"><time datetime="2022-01-07T00:00:00-05:00" itemprop="datePublished">January 07, 2022</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">Hints for Computer System Design</a></li>
-    
     <li itemscope=""><span class="entry-date"><time datetime="2020-12-21T00:00:00-05:00" itemprop="datePublished">December 21, 2020</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Design-patterns-for-container-based-distributed-systems">Design patterns for container-based distributed systems</a></li>
     
     <li itemscope=""><span class="entry-date"><time datetime="2020-12-14T00:00:00-05:00" itemprop="datePublished">December 14, 2020</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Cassandra-a-decentralized-structured-storage-system">Cassandra - a decentralized structured storage system</a></li>
@@ -4905,8 +4947,6 @@ <h2 id="Synchronous+SGD">Synchronous SGD</h2>
   <h2 id="Systems">Systems</h2>
   <ul class="posts">
     
-    <li itemscope=""><span class="entry-date"><time datetime="2022-01-07T00:00:00-05:00" itemprop="datePublished">January 07, 2022</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Hints-for-Computer-System-Design">Hints for Computer System Design</a></li>
-    
     <li itemscope=""><span class="entry-date"><time datetime="2021-03-22T00:00:00-04:00" itemprop="datePublished">March 22, 2021</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/Deep-Neural-Networks-for-YouTube-Recommendations">Deep Neural Networks for YouTube Recommendations</a></li>
     
     <li itemscope=""><span class="entry-date"><time datetime="2021-03-15T00:00:00-04:00" itemprop="datePublished">March 15, 2021</time></span> &raquo; <a href="https://shagunsodhani.github.io/papers-I-read/The-Tail-at-Scale">The Tail at Scale</a></li>