QwenLM Qwen2.5 issues - Githubissues

QwenLM / Qwen2.5

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

9.38k stars 580 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

[Bug]: The final reason why you will get a model that cannot stop generation when you fine-tune the Qwen2.5-7b-base use Lora and a non-<|endoftext|> token as eos_token.

#1064 hxs91 opened 1 day ago
0
[Bug]: 使用Qwen2.5-72B-Instruct-AWQ和Qwen2.5-32B-Instruct-AWQ官方给的演示例子，运行的时候提示：returned non-zero exit status 1

#1059 SuSuStarSmile opened 2 days ago
0
A simplified version of the inference code ?

#1057 weizhenhuan opened 3 days ago
0
[Bug]: Use of the term "open source" to describe qwen when the training data is not open

#1055 phly95 opened 3 days ago
3
[Bug]: Model name error in vllm deployment

#1052 JulioZhao97 closed 5 days ago
4
[Bug]: AttributeError: Model Qwen2ForCausalLM does not support BitsAndBytes quantization yet.

#1049 yananchen1989 opened 1 week ago
1
[Bug]: can not deploy qwen2.5 with vllm

#1048 joyyyhuang closed 1 week ago
1
Rebuild docs for speed benchmark

#1045 wangxingjun778 closed 3 days ago
0
Add Qwen2.5 perf report

#1044 wangxingjun778 closed 1 week ago
0
add vllm version warning

#1043 jklj077 closed 1 week ago
0
[Badcase]: 用mlx框架把Qwen2.5-3B-Instruct转换为mlx版本后，又用mlx_lm.convert把mlx版本的模型进行int4量化，最后进行推理的时候报错：ValueError: [dequantize] The matrix should be given as a uint32

#1041 ghoshadow opened 1 week ago
0
[REQUEST]:

#1040 DAAworld closed 4 days ago
1
[Bug]: 模型回答时极大概率出现�

#1039 GitHub-lql opened 1 week ago
2
[Bug]: 使用 Xinference vLLM 启动 qwen2.5-32b-instruct 推理结果都是感叹号

#1038 andylzming opened 1 week ago
3
[Badcase]: Qwen2.5-7B-Instruct few shot能力很差，具体MedBench的SMDoc数据集

#1032 tzyodear opened 2 weeks ago
0
[Bug]: vllm启动大模型，超过一定的上下文长度导致大模型回答答非所问

#1031 Ave-Maria closed 2 weeks ago
3
[Bug]: 对lora merge后的模型量化，量化后模型输出一直出现human：

#1029 shenshaowei opened 2 weeks ago
3
Add modelers to README.md

#1028 vvmumu opened 2 weeks ago
0
[Badcase]:

#1027 zhuzcalex opened 2 weeks ago
0
[Badcase]: openai.BadRequestError: Error code: 400 - {'error': {'message': 'unexpected EOF', 'type': 'invalid_request_error', 'param': None, 'code': None}}

#1026 XyLove0223 opened 2 weeks ago
5
[Bug]: Qwen2.5-14B-Instruct-GPTQ-Int4存在严重的复读机和幻觉现象

#1024 yang-collect opened 3 weeks ago
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 SolomonLeon opened 3 weeks ago
3
Qwen2.5-1.5b用LLaMA-factory lora微调后，vLLM加载模型报错，求教~

#1022 Jimmy-L99 closed 3 weeks ago
0
[Badcase]: qwen2.5一定概率生成\\n

#1021 520jefferson closed 3 weeks ago
1
[Bug]: qwen2.5-72b-insruct math 自测分数和榜单分数差异较大

#1020 tianshiyisi closed 2 weeks ago
7
[Bug]: vLLM got different results with PeftModelForCausalLM

#1018 chansonzhang opened 3 weeks ago
3
[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 Jayc-Z opened 3 weeks ago
1
[Bug]: vllm 启动，openai的swarm 函数调用不正常

#1015 18600709862 opened 3 weeks ago
2
[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 yanli789 opened 3 weeks ago
3
[Bug]: No heartbeat received from MQLLMEngine

#1013 hulk-zhk opened 3 weeks ago
0
[Bug]: Qwen 2.5 tool calls change function names after response

#1012 LuckLittleBoy opened 4 weeks ago
3
[REQUEST]: Qwen的性能报告能否把首Token延迟也提供一下

#1011 zhufeizzz opened 4 weeks ago
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 ericg108 opened 4 weeks ago
1
[Bug]: vllm部署Qwen2.5-72B-Instruct压测出现报错

#1008 WangJianQ-0118 opened 1 month ago
1
[REQUEST]: Add finetuning scripts

#1007 chansonzhang opened 1 month ago
1
[Bug]: Nvidia L20推理Qwen2.5 72B GPTQ-Int8模型不符合预期

#1006 renne444 opened 1 month ago
8
[Badcase]: 使用Qwen2-7b翻译中文，有额外的输出

#1005 cjjjy opened 1 month ago
2
[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 1gst opened 1 month ago
3
[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 daimashenjing opened 1 month ago
4
docs: Add OpenLLM

#996 Sherlock113 closed 1 week ago
3
关于function参数的格式问题

#994 XuyangHao123 closed 1 month ago
0
[Badcase]: qwen2.5-72b 在昇腾910推理结果不符合预期

#992 tianshiyisi opened 1 month ago
6
[Badcase]: 函数调用出现不正常token（iNdEx）

#991 abiaoa1314 opened 1 month ago
1
mlx-lm documentation is corrected

#990 gringocl closed 3 weeks ago
0
[Badcase]: Qwen2.5-72B-Instruct-GPTQ-Int4 input_size_per_partition

#986 hyliush opened 1 month ago
6
[Badcase]: Qwen2.5 14B Instruct can't stop generation

#985 Jeremy-Hibiki opened 1 month ago
1
[Question]: 本地部署Qwen2后的文件上传问题

#983 Patrick24080735 closed 1 month ago
1
add fine-tuning readme for llama-factory

#982 yangjianxin1 closed 3 weeks ago
1
update doc

#981 jklj077 closed 1 month ago
0
[Question]: From which version at least, the vllm supports to infrence and serve Qwen2.5-14B-Instruct model?

#960 zengqingfu1442 closed 1 month ago
0