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

932 Open 845 Closed
932 Open 845 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

unsloth是否支持类似deepseepd zero的方式
#2276 opened Apr 3, 2025 by 256785
[BUG] unslothai/llama.cpp build error bug
#2275 opened Apr 3, 2025 by calvin2021y
1
4bit with VLLM: ValueError: There is no module or parameter named 'language_model' in Gemma3ForCausalLM bug
#2274 opened Apr 3, 2025 by ignaceHelsen
[QST] how to train gemma-1b properly
#2273 opened Apr 3, 2025 by hongye-liu
[BUG] Unable to create tensor when training Gemma 3 in Collab using custom dataset bug
#2270 opened Apr 3, 2025 by adamtcdev
1
[QST] Are there plans to add support for TRL 0.16.0 with the latest GRPO improvements they added? feature request Feature request pending on roadmap
#2269 opened Apr 2, 2025 by arnavgarg1
3
[FEAT] Rust rewrite feature request Feature request pending on roadmap
#2268 opened Apr 2, 2025 by brrock
1
[DOC] Gemma 3 instructions on Vision Fine Tuning page is not correct
#2265 opened Apr 2, 2025 by SharbelWired
1 task
3
[BUG] Unable to load deepseek-ai/DeepSeek-Coder-V2-Lite-Base for GRPO bug
#2262 opened Apr 1, 2025 by CuppaXanax
1
[BUG] unsloth/Inference with Mistral Small 3.1
#2261 opened Apr 1, 2025 by ServientShao
4
[BUG] Gemma3 vision throws error: TypeError: 'int' object is not iterable bug
#2258 opened Apr 1, 2025 by Nazzaroth2
1
[BUG] Evaluation & custom compute_metrics don't receive coherent text bug
#2257 opened Apr 1, 2025 by hugohabicht01
[QST] Running Model "unsloth/DeepSeek-V3-0324-GGUF" with vLLM does not working
#2254 opened Apr 1, 2025 by SSPRATAP17
2
AssertionError in cross_entropy_loss backward pass when targeting embed_tokens/lm_head with LoRA on fp16 hardware bug
#2253 opened Mar 31, 2025 by rupaut98
1
[BUG] Direct module loading failed: Error when loading SmolVLM2-2.2B-Instruct bug unsloth compile Issues related to unsloth compiler
#2252 opened Mar 31, 2025 by alvanli
1
[BUG] Image features and image tokens do not match on full finetuning bug
#2251 opened Mar 31, 2025 by alvanli
1
[QST] Can you share a reference notebook or piece of code on how to VISION finetune GEMMA3
#2249 opened Mar 31, 2025 by Abhinay2323
1
[BUG] Issue Loading Qwen2.5 models in Unsloth with Transformers > 4.45.0 bug
#2243 opened Mar 31, 2025 by afspies
2
Embedding matrix size did not get resized properly, while trying to add new tokens on Ministral-8B finetunes.
#2241 opened Mar 30, 2025 by SuperMasterBlasterLaser
Lora saving issue lora save / load Inconsistent results after `save_lora` / `load_lora`
#2240 opened Mar 30, 2025 by ItzAmirreza
4
RuntimeError: Unsloth: Saving LoRA finetune failed since # of LoRAs = 196 does not match # of saved modules = 392. Please file a bug report!
#2238 opened Mar 30, 2025 by embedded-robotics
1
Pre-training Gemma3 27B with short context fails
#2237 opened Mar 29, 2025 by etemiz
2
lora fine-tuning qwq32B error
#2235 opened Mar 29, 2025 by tiger-rgb
1
When will multimodal grpo fine-tuning be supported?
#2232 opened Mar 29, 2025 by chaodreaming
2
BackendCompilerFailed: backend='inductor' raised: SystemError: PY_SSIZE_T_CLEAN macro must be defined for '#' formats
#2230 opened Mar 28, 2025 by Serjio42
2
ProTip! What’s not been updated in a month: updated:<2025-03-03.