Skip to content

Issues: QwenLM/Qwen2.5

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

53 Open 785 Closed
53 Open 785 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

[Badcase]:
#1027 opened Oct 21, 2024 by zhuzcalex
4 tasks done
@yangapku
[Badcase]: openai.BadRequestError: Error code: 400 - {'error': {'message': 'unexpected EOF', 'type': 'invalid_request_error', 'param': None, 'code': None}}
#1026 opened Oct 20, 2024 by XyLove0223
4 tasks done
5
[Bug]: Qwen2.5-14B-Instruct-GPTQ-Int4存在严重的复读机和幻觉现象
#1024 opened Oct 18, 2024 by yang-collect
4 tasks done
7
[Bug]: 在 4 卡 16GB V100 机器上采用 lmdeploy 部署 qwen2.5-32b-instruct-gptq-int4 模型，最高输出速度只有 80token/s ，请问这个速度正常吗？
#1023 opened Oct 17, 2024 by SolomonLeon
4 tasks done
[Bug]: vLLM got different results with PeftModelForCausalLM
#1018 opened Oct 15, 2024 by chansonzhang
4 tasks done
2
[Badcase]: 相同的微调数据，Qwen1.5 14B准确率比Qwen2.5 14B高20%左右，这是什么原因
#1016 opened Oct 15, 2024 by Jayc-Z
4 tasks done
[Bug]: vllm 启动，openai的swarm 函数调用不正常
#1015 opened Oct 15, 2024 by 18600709862
4 tasks done
1
[Bug]:模型加载参数精度及显存占用不符合预期，无法用int4精度加载量化后的模型Qwen2.5-7B-Instruct-GPTQ-Int4
#1014 opened Oct 15, 2024 by yanli789
4 tasks done
3
[Bug]: No heartbeat received from MQLLMEngine
#1013 opened Oct 14, 2024 by hulk-zhk
4 tasks done
[Bug]: Qwen 2.5 tool calls change function names after response
#1012 opened Oct 12, 2024 by LuckLittleBoy
4 tasks done
3
[REQUEST]: Qwen的性能报告能否把首Token延迟也提供一下
#1011 opened Oct 12, 2024 by zhufeizzz
4 of 5 tasks
1
[Bug]: Qwen2.5-72B-instruct使用vllm部署通过函数调用输出的结果里所有汉字被转义了
#1009 opened Oct 11, 2024 by ericg108
4 tasks done
[Bug]: vllm部署Qwen2.5-72B-Instruct压测出现报错
#1008 opened Oct 10, 2024 by WangJianQ-0118
4 tasks done
1
[REQUEST]: Add finetuning scripts
#1007 opened Oct 10, 2024 by chansonzhang
4 of 5 tasks
[Bug]: Nvidia L20推理Qwen2.5 72B GPTQ-Int8模型不符合预期
#1006 opened Oct 8, 2024 by renne444
4 tasks done
5
[Badcase]: 使用Qwen2-7b翻译中文，有额外的输出
#1005 opened Oct 6, 2024 by cjjjy
4 tasks done
1
[Bug]: vllm部署后，用官方的例子调用报错openai.BadRequestError: Error code: 400 - {'object': 'error', 'message': "name 'Extension' is not defined", 'type': 'BadRequestError', 'param': None, 'code': 400}
#998 opened Sep 29, 2024 by 1gst
4 tasks done
2
[Bug]: 文档问答会忽略部分数据，比如证书号是12345 回答的是2345
#997 opened Sep 29, 2024 by daimashenjing
4 tasks done
3
[Badcase]: qwen2.5-72b 在昇腾910推理结果不符合预期 help wanted Extra attention is needed
#992 opened Sep 28, 2024 by tianshiyisi
4 tasks done
4
[Badcase]: 函数调用出现不正常token（iNdEx）
#991 opened Sep 27, 2024 by abiaoa1314
4 tasks done
@JianxinMa
[Badcase]: Qwen2.5-72B-Instruct-GPTQ-Int4 input_size_per_partition
#986 opened Sep 26, 2024 by hyliush
4 tasks done
5
[Badcase]: Qwen2.5 14B Instruct can't stop generation enhancement New feature or request
#985 opened Sep 26, 2024 by Jeremy-Hibiki
4 tasks done
@yangapku
1
[Bug]: Qwen2 moe out of memory
#954 opened Sep 25, 2024 by FL77N
4 tasks done
2
[REQUEST]: working tool call configuration with localai
#949 opened Sep 23, 2024 by codefromthecrypt
4 of 5 tasks
[Badcase]: Model inference Qwen2.5-32B-Instruct-GPTQ-Int4 appears as garbled text !!!!!!!!!!!!!!!!!!
#945 opened Sep 23, 2024 by zhanaali
4 tasks done
@hzhwcmhf
16
ProTip! Exclude everything labeled bug with -label:bug.