-
-
Notifications
You must be signed in to change notification settings - Fork 808
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Why do training lm_head and embed_tokens require converting accuracy to fp32
#633
opened Jun 13, 2024 by
letterk
Quantization error-(model.save_pretrained_gguf("model", tokenizer,))
#661
opened Jun 18, 2024 by
handsomechang114514
ORPO Unsloth Example.ipynb not showing logging_steps
currently fixing
Am fixing now!
#657
opened Jun 17, 2024 by
MarjovanLier
LLVM ERROR: Cannot select: intrinsic %llvm.nvvm.shfl.sync.bfly.i32 Aborted
#642
opened Jun 14, 2024 by
mathysferrato
issue with 70B instruct models (llama-3-70b-Instruct-bnb-4bit, Qwen2-72B-Instruct-bnb-4bit)
#635
opened Jun 13, 2024 by
taejoon89
TypeError: Unsloth: Your model already has LoRA adapters. No need to run this again!
#631
opened Jun 13, 2024 by
subhamiitk
NotImplementedError: Unsloth: Writer/palmyra-med-20b not supported yet!
#618
opened Jun 11, 2024 by
tonnguyen-pts
RuntimeError: Unsloth:
unsloth/llama-3-8b-bnb-4bit
is not a full model or a PEFT model.
#614
opened Jun 10, 2024 by
Lipapaldl
Kernel suddenly dies, not sure why. WSL - Ubuntu, Conda install issues
#613
opened Jun 10, 2024 by
Chesqoo
ProTip!
Find all open issues with in progress development work with linked:pr.