Skip to content

Issues: hiyouga/LLaMA-Factory

🚨FAQs | 常见问题🚨
#4614 opened Jun 28, 2024 by hiyouga
Open
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

254 Open 5,557 Closed
254 Open 5,557 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

Qwen2.5-VL full sft dtype error bug Something isn't working pending This problem is yet to be addressed
#6791 opened Feb 2, 2025 by wyuc
1 task done
Version of the 'liger_kernel' and 'unsloth' bug Something isn't working pending This problem is yet to be addressed
#6790 opened Feb 2, 2025 by Fangkang515
1 task done
ValueError: The checkpoint you are trying to load has model type llava_mistral but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date. bug Something isn't working pending This problem is yet to be addressed
#6781 opened Jan 30, 2025 by dainini
1 task done
有计划支持Deepseek的janus pro微调么 enhancement New feature or request pending This problem is yet to be addressed
#6775 opened Jan 28, 2025 by mkygogo
1 task done
1
Q_APOLLO? enhancement New feature or request pending This problem is yet to be addressed
#6774 opened Jan 28, 2025 by inflatebot
1 task done
希望支持RFT微调方法。 enhancement New feature or request pending This problem is yet to be addressed
#6763 opened Jan 26, 2025 by bhnan
1 task done
One of the subprocesses has abruptly died during map operation.To debug the error, disable multiprocessing. 无论numworkers多大都没用 bug Something isn't working pending This problem is yet to be addressed
#6762 opened Jan 25, 2025 by miaowuawa
1 task done
1
does save_strategy conflicts with save_total_limit? bug Something isn't working pending This problem is yet to be addressed
#6761 opened Jan 25, 2025 by VoiceBeer
1 task done
3
tie_word_embeddings=True的模型，新增new_special_tokens，只训练embed_token和同时训练embed_token、lm_head存在问题 bug Something isn't working pending This problem is yet to be addressed
#6749 opened Jan 24, 2025 by mxzf0213
1 task done
能否支持在Qlora微调后直接导出int4等量化的模型 enhancement New feature or request pending This problem is yet to be addressed
#6747 opened Jan 24, 2025 by honglei56
1 task done
1
python scripts/vllm_infer.py执行模型批量推理报错Caught signal 8 (Floating point exception: integer divide by zero) bug Something isn't working pending This problem is yet to be addressed
#6741 opened Jan 23, 2025 by zdw-111
1 task done
command 'llamafactory-cli webui' failed to start if HTTP_PROXY is set bug Something isn't working pending This problem is yet to be addressed
#6739 opened Jan 22, 2025 by qiangyt
1 task done
请求支持 qwen2-audio enhancement New feature or request in-progress The related features are in the progress pending This problem is yet to be addressed
#6738 opened Jan 22, 2025 by superFilicos
1 task done
1
How to jump a single sample？ bug Something isn't working pending This problem is yet to be addressed
#6732 opened Jan 21, 2025 by sxj1215
1 task done
4
qwen2.5-32B-Instruct模型2机npu 910B训练结束后，保存模型时失败 bug Something isn't working npu This problem is related to NPU devices pending This problem is yet to be addressed
#6726 opened Jan 21, 2025 by chriszhangmq
1 task done
1
windows下微调llama3.1-instruction 开始训练后报错 无法启动微调 bug Something isn't working pending This problem is yet to be addressed
#6725 opened Jan 21, 2025 by LJXCMQ
1 task done
1
label smoothing 支持 enhancement New feature or request pending This problem is yet to be addressed
#6719 opened Jan 20, 2025 by 652994331
1 task done
please add bitune support enhancement New feature or request pending This problem is yet to be addressed
#6718 opened Jan 20, 2025 by chaitu0032
1 task done
qwen2_vl 模型 使用 vllm 引擎推理时对视频文件的传入未进行处理 bug Something isn't working enhancement New feature or request pending This problem is yet to be addressed
#6708 opened Jan 20, 2025 by imwxc
1 task done
Param Size Mismatch after Fine-tuned on Llama-3-8B-Instruct bug Something isn't working pending This problem is yet to be addressed
#6700 opened Jan 18, 2025 by bw-wang19
1 task done
1
Size mismatch error in the middle of training bug Something isn't working pending This problem is yet to be addressed
#6699 opened Jan 18, 2025 by NicoZenith
1 task done
1
自动被killed且无任何报错信息 bug Something isn't working pending This problem is yet to be addressed
#6687 opened Jan 17, 2025 by duyu09
1 task done
@hiyouga
1
deepspeed 容器环境下no-ssh多机多卡训练 bug Something isn't working pending This problem is yet to be addressed
#6685 opened Jan 17, 2025 by Justin-12138
1 task done
1
NPU基于Qwen2-VL-7B执行多卡QLoRA时卡住 bug Something isn't working npu This problem is related to NPU devices pending This problem is yet to be addressed
#6659 opened Jan 15, 2025 by tbozhong
1 task done
1
no success funtuning method with pissa in LLama Board，but it's ok using commanding line bug Something isn't working pending This problem is yet to be addressed
#6656 opened Jan 15, 2025 by chuangzhidan
1 task done
ProTip! Type g i on any issue or pull request to go back to the issue listing page.