Merge pull request #11 from for-ai/quick-updates

Quick updates on documentation and dependencies
for-ai · Jul 20, 2024 · 8555da7 · 8555da7
2 parents 13a1d02 + 78e3b03
commit 8555da7
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -29,18 +29,22 @@ export HF_TOKEN=<your huggingface token>
 You can find all runnable experiments in the `scripts` directory.
 Their filename should explicitly tell you their purpose. 
 
-## Running translation
+### Running translation
+
+ We currently use [`facebook/nllb-200-3.3B`](https://huggingface.co/facebook/nllb-200-3.3B) for translation. First install sentence splitter using: 
 
- We currently use `facebook/nllb-200-3.3B` for translation. First install sentence splitter using: 
  ```
  pip install git+https://github.com/mediacloud/sentence-splitter.git
  ```
+
  To translate reward bench into [22 Aya languages](https://arxiv.org/abs/2405.15032) run the following:
+
 ```  
 cd scripts
 bash run_nllb.sh
 ```
-You can also translate a specifc preference dataset from huggingface to a specifc target langauge using `scripts/translate_preference_pairs_nllb.py`.
+
+You can also translate a specifc preference dataset from huggingface to a specifc target language using `scripts/translate_preference_pairs_nllb.py`.
 
 ### Getting rewards from a Reward Model (RM) on a HuggingFace dataset
 

diff --git a/requirements.txt b/requirements.txt
@@ -9,3 +9,4 @@ together==1.2.1
 cohere==5.6.1
 git+https://github.com/lm-sys/FastChat.git@92a6d1fcd69a88ea169c0b01065ce44f1e690a2c
 python-dotenv
+sentence-splitter==1.4