-
Notifications
You must be signed in to change notification settings - Fork 5.5k
Issues: hiyouga/LLaMA-Factory
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
ppo训练报错(调用ppo_train)
bug
Something isn't working
pending
This problem is yet to be addressed
#7499
opened Mar 26, 2025 by
SetonLiang
1 task done
视觉模型api问题调用报错
bug
Something isn't working
pending
This problem is yet to be addressed
#7498
opened Mar 26, 2025 by
moro0v0
1 task done
设置了stream, max_steps ,算出来的epoch数量不对
bug
Something isn't working
pending
This problem is yet to be addressed
#7496
opened Mar 26, 2025 by
minmummax
1 task done
Class of Gemma3-pt set to AutoModelForCausalLM
bug
Something isn't working
pending
This problem is yet to be addressed
#7491
opened Mar 26, 2025 by
kwonmha
1 task done
310P卡推理失败
bug
Something isn't working
npu
This problem is related to NPU devices
pending
This problem is yet to be addressed
#7489
opened Mar 26, 2025 by
ChenZhongPu
1 task done
Training loss drops at the start of a new epoch
bug
Something isn't working
pending
This problem is yet to be addressed
#7485
opened Mar 25, 2025 by
SamuelLarkin
1 task done
position of bos token is not valid in Class PretrainDatasetProcessor
bug
Something isn't working
pending
This problem is yet to be addressed
#7484
opened Mar 25, 2025 by
JackJessada
1 task done
vllm_infer 批量推理 minicpm2.6-v 输入预处理出错
bug
Something isn't working
pending
This problem is yet to be addressed
#7483
opened Mar 25, 2025 by
ksnzh
1 task done
Detected ZeRO Offload and non-DeepSpeed optimizers: This combination should work as long as the custom optimizer has both CPU and GPU implementation (except LAMB)
bug
Something isn't working
pending
This problem is yet to be addressed
#7479
opened Mar 25, 2025 by
yangguoquan001
1 task done
Qwen2.5 多图微调时 出现TypeError: 'NoneType' object is not subscriptable错误
bug
Something isn't working
pending
This problem is yet to be addressed
#7477
opened Mar 25, 2025 by
han-lx
1 task done
继续训练增加epoch
bug
Something isn't working
pending
This problem is yet to be addressed
#7476
opened Mar 25, 2025 by
cqray1990
1 task done
Qwen2.5-coder-7B continue pretraining功能好像不支持,求指导
bug
Something isn't working
pending
This problem is yet to be addressed
#7475
opened Mar 25, 2025 by
xxhe504
1 task done
用【纯文本数据集】训练【多模态模型时】,报错
bug
Something isn't working
pending
This problem is yet to be addressed
#7470
opened Mar 25, 2025 by
pandayummy
1 task done
Does gemma3 now support training of reward models?
enhancement
New feature or request
pending
This problem is yet to be addressed
#7468
opened Mar 25, 2025 by
jinzhuoran
1 task done
RuntimeError: p.attn_bias_ptr is not correctly aligned
bug
Something isn't working
pending
This problem is yet to be addressed
#7460
opened Mar 24, 2025 by
1212wuhu
1 task done
Lora Parameter File Memory Difference
bug
Something isn't working
pending
This problem is yet to be addressed
#7459
opened Mar 24, 2025 by
czx-li
1 task done
Finetuning Base Model on chat data should change "eos_token" to "<|im_end|>
enhancement
New feature or request
pending
This problem is yet to be addressed
#7454
opened Mar 24, 2025 by
mertunsall
1 task done
Add support for vLLM-Ascend
enhancement
New feature or request
npu
This problem is related to NPU devices
pending
This problem is yet to be addressed
#7447
opened Mar 24, 2025 by
leo-pony
1 task done
llama3.2 vision
bug
Something isn't working
pending
This problem is yet to be addressed
#7446
opened Mar 23, 2025 by
orcnnn
1 task done
longlora版本冲突
bug
Something isn't working
pending
This problem is yet to be addressed
#7434
opened Mar 23, 2025 by
salvatoreferragamo
1 task done
New model supports: nvidia/Llama-3_3-Nemotron-Super-49B-v1 and nvidia/Llama-3.1-Nemotron-Nano-8B-v1
enhancement
New feature or request
pending
This problem is yet to be addressed
#7430
opened Mar 22, 2025 by
jqwang2373
1 task done
Gemma3 finetuning using adam mini not working
bug
Something isn't working
pending
This problem is yet to be addressed
#7429
opened Mar 22, 2025 by
AbdelrhmanNile
1 task done
RuntimeError: Internal Triton PTX codegen error
bug
Something isn't working
pending
This problem is yet to be addressed
#7417
opened Mar 22, 2025 by
275244143
1 task done
Invalid Something isn't working
pending
This problem is yet to be addressed
throughput
after resuming
bug
#7415
opened Mar 21, 2025 by
SamuelLarkin
1 task done
Previous Next
ProTip!
Find all open issues with in progress development work with linked:pr.