Skip to content

Issues: unslothai/unsloth

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

755 Open 659 Closed
755 Open 659 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

!handles_.at(i) INTERNAL ASSERT FAILED at "../c10/cuda/CUDACachingAllocator.cpp":393, please report a bug to PyTorch.
#1819 opened Feb 24, 2025 by arch-one
1
Unsloth GRPO trainer error - IndexError: argmax(): Expected reduction dim 1 to have non-zero size.
#1817 opened Feb 24, 2025 by w601sxs
r1-reasoning verification
#1816 opened Feb 24, 2025 by zstang
GRPO with Qwen2.5-VL support？
#1815 opened Feb 24, 2025 by shiyongde
Loading Fine-Tuned LLaMA with LoRA Using AutoModelForCausalLM – Are LoRA Weights Applied Correctly
#1814 opened Feb 24, 2025 by Hyfred
Support SmolVLM2
#1813 opened Feb 24, 2025 by Rm1n90
Support For Qwen-2.5 GRPO Training
#1812 opened Feb 24, 2025 by JamesBowerXanda
Model parameters saved during training are incorrect
#1811 opened Feb 24, 2025 by Kathrine94
GRPO without VLLM?
#1810 opened Feb 24, 2025 by DaddyCodesAlot
1
Llama AttributeError: 'bool' object has no attribute 'all_special_tokens'
#1809 opened Feb 24, 2025 by mattguida
2
KeyError: 'completion_length' in GRPO trainer currently fixing Am fixing now!
#1807 opened Feb 23, 2025 by monk1337
1
2
Trainer automatically converts dataset to ChatML despite using Llama chat template in recent version currently fixing Am fixing now!
#1802 opened Feb 22, 2025 by FOCUSLLM
4
VRAM spikes after "LlamaForCausalLM does not accept 'num_items_in_batch'"
#1801 opened Feb 22, 2025 by RWTHEY
2
lowering model name when model downloaded makes additional downloading
#1798 opened Feb 22, 2025 by Redix8
1
CUDA error: out of memory in WSL with 24G VRAM while 2/3 was still left unused
#1797 opened Feb 22, 2025 by ja3592
2
Question about the batch size in new GRPO
#1796 opened Feb 22, 2025 by AIR-hl
1
Training data preprocessing and template issues
#1795 opened Feb 22, 2025 by supperman009
1
support NPU? feature request Feature request pending on roadmap
#1794 opened Feb 22, 2025 by RyanOvO
2
partially initialized module 'torchvision' has no attribute 'extension'
#1793 opened Feb 22, 2025 by z-x-x136
3
Failure!! Saving to safetensors, not bin format in Colab
#1792 opened Feb 22, 2025 by elvis324
1
[BUG] 'merge_4bit_forced' missing custom logic to save 4-bit dynamic quant currently fixing Am fixing now!
#1791 opened Feb 21, 2025 by ColumbusAI
1
New GRPO doesnt support models besides LLAMA - (Mistral)
#1790 opened Feb 21, 2025 by advpropsys
5
No label_names provided for model class PeftModelForCausalLM. Since PeftModel hides base models input arguments, if label_names is not given, label_names can't be set automatically within Trainer.
#1788 opened Feb 21, 2025 by Ahmed-Hassany
3
fine-tuned llama3.1 models keeps repeating itself
#1787 opened Feb 21, 2025 by lchehecl
Unablr to run GRPO in Runpod currently fixing Am fixing now!
#1785 opened Feb 21, 2025 by ppraneth
1
ProTip! What’s not been updated in a month: updated:<2025-01-24.