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

720 Open 640 Closed
720 Open 640 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

Error loading llama 3.1 8B instruct
#1751 opened Feb 18, 2025 by tristan279
AttributeError: 'PeftModelForCausalLM' object has no attribute '_unwrapped_old_generate'
#1749 opened Feb 18, 2025 by stromyu520
Update preprocessor_config.json for Qwen2.5-VL models on huggingface
#1747 opened Feb 18, 2025 by Tahirc1
How much impact does the system prompt have on the output results?
#1746 opened Feb 18, 2025 by LaFeuilleMorte
OOM on Local GRPOTrainer
#1744 opened Feb 18, 2025 by zhzLuke96
1
I can't pip install "unsloth[colab-new]@git+https://github.com/unslothai/unsloth.git"
#1743 opened Feb 18, 2025 by jiupinjiandingshi
3
Output deterioration with model.eval() (unsloth/Meta-Llama-3.1-8B)
#1742 opened Feb 18, 2025 by yoakiyama
non-default argument follows default argument (UnslothGKDTrainer.py, line 613) currently fixing Am fixing now!
#1741 opened Feb 18, 2025 by elvis324
4
Low-Quality and Repetitive Text Generation in FastLanguageModel instead of AutoModelForCausalLM
#1740 opened Feb 18, 2025 by Hyfred
1
Vast.ai implementation
#1734 opened Feb 17, 2025 by edoproch
retrieve training parameters from a lora model?
#1733 opened Feb 17, 2025 by ep0p
Problems using evaluation
#1731 opened Feb 17, 2025 by edoproch
2
Add Reward Model support
#1730 opened Feb 17, 2025 by weiminw
PreTrainedTokenizerFast has no attribute _ollama_modelfile
#1729 opened Feb 17, 2025 by leonlee723
while training unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit why it is showning applying chat template .
#1728 opened Feb 17, 2025 by SnehaKumari14
4
abnormal model output '!!!!!!!!!!!!' at new version currently fixing Am fixing now!
#1727 opened Feb 17, 2025 by zuozhenLib
5
Getting error with loading Llama unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
#1726 opened Feb 16, 2025 by SnehaKumari14
3
CalledProcessError: Command xxx returned non-zero exit status 2.
#1725 opened Feb 16, 2025 by QiXingRan
AttributeError: _unwrapped_old_generate
#1724 opened Feb 16, 2025 by ylwlf888
AttributeError: _unwrapped_old_generate currently fixing Am fixing now!
#1723 opened Feb 16, 2025 by ylwlf888
2
Why does unsloth grpo still need 'answer' as input data?
#1722 opened Feb 15, 2025 by zhangxuefeng
3
OOM error when i tried to save model in q_8 gguf
#1721 opened Feb 15, 2025 by Mracobes9
1
Feature Request: Finetune DeepSeek (and other MoEs) to use Pregate for predictive MoE offloading and fetching feature request Feature request pending on roadmap
#1719 opened Feb 15, 2025 by Thomas-MMJ
1
RuntimeError: The size of tensor a (2048) must match the size of tensor b (4241) at non-singleton dimension 1
#1717 opened Feb 15, 2025 by azzedineA
9
GPRO training alpha
#1715 opened Feb 15, 2025 by Hert4
1
ProTip! What’s not been updated in a month: updated:<2025-01-18.