Skip to content

Issues: QwenLM/Qwen2

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

121 Open 464 Closed
121 Open 464 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

ollama部署Qwen2-72B-Instruct模型，出现token超出1024限制的提示
#711 opened Jun 27, 2024 by lucumt
1
RuntimeError: cutlassF: no kernel found to launch!
#710 opened Jun 27, 2024 by BryanMurkyChan
2
Qwen2-7B-Instruct's performance gaps in evaluations of the GSM8K and MATH datasets with official scores
#709 opened Jun 27, 2024 by ArixLi
@hzhwcmhf
qwen2 finetune 报错
#708 opened Jun 26, 2024 by xsank
2
基于qwen1.5 14B 100k训练重复
#707 opened Jun 26, 2024 by 520jefferson
1
AttributeError: 'Qwen2ForCausalLM' object has no attribute 'merge_and_upload'
#706 opened Jun 25, 2024 by haidong-Ding
1
0.5b 的模型增量预训练loss下降慢，想问问有啥更好的配置？
#705 opened Jun 25, 2024 by wizardforcel
2
Rag应用中，Qwen2无法回答2023年后的问题，总是回答"更新截止时间xx年xx","由于我无法实时获取信息，我无法提供2024年的"等生成内容
#701 opened Jun 24, 2024 by zhangjiekui
@JianxinMa
1
qwen2 1.5B 评测结果无法对齐
#700 opened Jun 24, 2024 by momoyrz
@hzhwcmhf @liudayiheng
3
模型在sft/finetune.py中进行微调训练的时候遇到了错误
#696 opened Jun 24, 2024 by CmyLjj
1
使用lm 加载qwen2 7b 设置flashattention 依然回复GGGGGGG 使用cpu又是乱码~
#694 opened Jun 23, 2024 by liu-super
1
Cuda memory while finetuning
#693 opened Jun 22, 2024 by abpani
3
能不能针对qwen2-moe提供一个modeling_qwen2_moe.py的megatron转化特供版
#687 opened Jun 21, 2024 by steins048596
1
Potential use cases for Qwen-0.5B discussion Open for discussion
#685 opened Jun 20, 2024 by Tejaswgupta
2
有无量化到24gB以内的？
#684 opened Jun 20, 2024 by DoiiarX
4
qwen2量化的模型微调，loss不收敛
#676 opened Jun 19, 2024 by DuBaiSheng
2
Qwen2-72B-Instruct-gptq-int4重复问题 enhancement New feature or request
#675 opened Jun 19, 2024 by Storm0921
13
再次预训练
#667 opened Jun 18, 2024 by wangxun6
1
When running the cli_demo file, how can I resolve the _queue.Empty issue?
#657 opened Jun 17, 2024 by wulixianming
5
提示失败 enhancement New feature or request
#591 opened Jun 15, 2024 by wencan
Qwen2-72B-Instruct-GPTQ-Int8模型的量化问题
#578 opened Jun 15, 2024 by Sebastian-Getts
@hzhwcmhf
12
使用vllm部署qwen2-72b-instruct重复生成的问题
#576 opened Jun 14, 2024 by Kk1984up
3
docker镜像拉取失败 wontfix This will not be worked on
#572 opened Jun 14, 2024 by wells-Qiang-Chen
4
Qwen2-7B-instruct在HumanEval上的表现达到了79.9，但是在qwen1提示词的情况下，复现只有62，能否公开qwen2的部分测试提示词？
#569 opened Jun 13, 2024 by aa327chenge
@huybery
4
用qwen1.5-32B-chat测试langgraph的官方例子时无法调用function，所有代码均按照langgraph的notbook写，仅仅替换了模型，模型是fschat本地服务器部署的，请问问题出在哪？
#568 opened Jun 13, 2024 by aimi0914
4
ProTip! no:milestone will show everything without a milestone.