Search results

Qwen2.5-3B模型 OOM

bugSomething isn't workingSomething isn't working

pendingThis problem is yet to be addressedThis problem is yet to be addressed

Status: Open.

#6752 In hiyouga/LLaMA-Factory;

· weilx2267 opened on Jan 24, 2025

希望能增加对huggingface transfer的支持

enhancementNew feature or requestNew feature or request

pendingThis problem is yet to be addressedThis problem is yet to be addressed

Status: Open.

#6750 In hiyouga/LLaMA-Factory;

· ameryzhu opened on Jan 24, 2025

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

bugSomething isn't workingSomething isn't working

pendingThis problem is yet to be addressedThis problem is yet to be addressed

Status: Open.

#6749 In hiyouga/LLaMA-Factory;

· mxzf0213 opened on Jan 24, 2025

能否支持在Qlora微调后直接导出int4等量化的模型

enhancementNew feature or requestNew feature or request

pendingThis problem is yet to be addressedThis problem is yet to be addressed

Status: Open.

#6747 In hiyouga/LLaMA-Factory;

· honglei56 opened on Jan 24, 2025

训练出错，cuda缺少libcusparse.so.11，更新重装都没用，请大佬帮忙看看，感谢

bugSomething isn't workingSomething isn't working

pendingThis problem is yet to be addressedThis problem is yet to be addressed

Status: Open.

#6742 In hiyouga/LLaMA-Factory;

· sgg-comeon opened on Jan 23, 2025

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)

bugSomething isn't workingSomething isn't working

pendingThis problem is yet to be addressedThis problem is yet to be addressed

Status: Open.

#6741 In hiyouga/LLaMA-Factory;

· zdw-111 opened on Jan 23, 2025

command 'llamafactory-cli webui' failed to start if HTTP_PROXY is set

bugSomething isn't workingSomething isn't working

pendingThis problem is yet to be addressedThis problem is yet to be addressed

Status: Open.

#6739 In hiyouga/LLaMA-Factory;

· qiangyt opened on Jan 22, 2025

请求支持 qwen2-audio

enhancementNew feature or requestNew feature or request

in-progressThe related features are in the progressThe related features are in the progress

pendingThis problem is yet to be addressedThis problem is yet to be addressed

Status: Open.

#6738 In hiyouga/LLaMA-Factory;

· superFilicos opened on Jan 22, 2025

请问：是否支持微调 DeepSeek-R1-Distill 系列模型？

enhancementNew feature or requestNew feature or request

pendingThis problem is yet to be addressedThis problem is yet to be addressed

Status: Open.

#6737 In hiyouga/LLaMA-Factory;

· CsBoBoNice opened on Jan 22, 2025

How to jump a single sample？

bugSomething isn't workingSomething isn't working

pendingThis problem is yet to be addressedThis problem is yet to be addressed

Status: Open.

#6732 In hiyouga/LLaMA-Factory;

· sxj1215 opened on Jan 21, 2025

qwen2.5-32B-Instruct模型2机npu 910B训练结束后，保存模型时失败

bugSomething isn't workingSomething isn't working

npuThis problem is related to NPU devicesThis problem is related to NPU devices

pendingThis problem is yet to be addressedThis problem is yet to be addressed

Status: Open.

#6726 In hiyouga/LLaMA-Factory;

· chriszhangmq opened on Jan 21, 2025

windows下微调llama3.1-instruction 开始训练后报错 无法启动微调

bugSomething isn't workingSomething isn't working

pendingThis problem is yet to be addressedThis problem is yet to be addressed

Status: Open.

#6725 In hiyouga/LLaMA-Factory;

· LJXCMQ opened on Jan 21, 2025