Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / QwenLM/Qwen2.5 issues and pull requests

#72 - vllm deploy with stop_token_ids

Issue - State: closed - Opened by geasyheart 9 months ago - 5 comments

#71 - qwen1.5-72B-gptq-int4 vllm-gptq报错

Issue - State: closed - Opened by Jankin66 9 months ago - 2 comments

#71 - qwen1.5-72B-gptq-int4 vllm-gptq报错

Issue - State: closed - Opened by Jankin66 9 months ago - 2 comments

#70 - delete build

Pull Request - State: closed - Opened by JustinLin610 9 months ago

#70 - delete build

Pull Request - State: closed - Opened by JustinLin610 9 months ago

#69 - add yaml

Pull Request - State: closed - Opened by JustinLin610 9 months ago

#68 - add docs and finetune scripts

Pull Request - State: closed - Opened by JustinLin610 9 months ago

#67 - vllm 72b启动失败

Issue - State: closed - Opened by icevivian 9 months ago - 7 comments

#66 - 这是很棒的模型但有个问题

Issue - State: closed - Opened by win10ogod 9 months ago - 2 comments

#65 - Auto-GPTQ qwen2 not support yet

Issue - State: closed - Opened by su-zelong 9 months ago - 6 comments

#64 - 速度比qwen变慢了很多

Issue - State: closed - Opened by 1920853199 9 months ago - 5 comments

#63 - Qwen-14B-Chat-Int4 vllm部署失败

Issue - State: closed - Opened by lichtud 9 months ago - 7 comments

#62 - [Feature Request]GQA and SWA support

Issue - State: closed - Opened by Pevernow 9 months ago - 1 comment

#61 - update README.md

Pull Request - State: closed - Opened by hzhwcmhf 9 months ago

#60 - [BUG] Qwen1.5-72B-Chat gguf 乱回答

Issue - State: closed - Opened by zhengxingmao 9 months ago - 6 comments

#59 - [BUG] Qwen1.5-1.8B-Chat转换成gguf报错

Issue - State: closed - Opened by anaivebird 9 months ago - 6 comments

#58 - 关于qwen与qwen1.5的lora微调层名差异导致微调参数量区别

Issue - State: closed - Opened by fanbooo 9 months ago - 3 comments

#57 - Qwen1.5-1.8B-Chat转换成gguf报错

Issue - State: closed - Opened by anaivebird 9 months ago - 10 comments

#55 - 支持function call吗

Issue - State: closed - Opened by xianzhisheng 9 months ago - 8 comments

#54 - 我本地可以跑qwen1 的72b int4， 但是跑不了qwen1.5的72b int4

Issue - State: closed - Opened by papandadj 9 months ago - 3 comments

#53 - Qwen1.5支持peft库进行lora微调么

Issue - State: closed - Opened by WangXinghuo 9 months ago - 2 comments

#52 - 有同学部署qwen1.5可以正常聊天吗

Issue - State: closed - Opened by ticoAg 9 months ago - 9 comments

#51 - webui可以提供一个支持qwenv1.5的版本么？

Issue - State: closed - Opened by moseshu 9 months ago - 3 comments

#50 - 1.5-72B-Chat 显存占用270GB，推理速度只有3 Tokens/s

Issue - State: closed - Opened by tianshiyisi 9 months ago - 7 comments

#49 - VLLM还不支持Qwen1.5是吗？

Issue - State: closed - Opened by Jankin66 9 months ago - 5 comments
Labels: question

#45 - Exllamav2 Backend Support Plz.

Issue - State: closed - Opened by Pevernow 9 months ago - 1 comment

#43 - Bad result in Qwen1.5-0.5B-Chat-GGUF

Issue - State: closed - Opened by xd2333 9 months ago - 2 comments

#41 - use qwen1.5 with vllm default prompt template?

Issue - State: closed - Opened by 2533245542 9 months ago - 1 comment

#40 - How to enable flash attention 2?

Issue - State: closed - Opened by LinB203 9 months ago - 5 comments

#38 - AttributeError: 'Qwen2ForCausalLM' object has no attribute 'chat_stream'

Issue - State: closed - Opened by wrl1224 9 months ago - 12 comments

#37 - AttributeError: 'Qwen2ForCausalLM' object has no attribute 'chat'

Issue - State: closed - Opened by zyy543370785 9 months ago - 7 comments

#33 - what's the difference of <|im_end|> and <|endoftext|>?

Issue - State: closed - Opened by BlueBlueFF 9 months ago - 1 comment

#32 - 7B-Chat-GPTQ-Int4 "disable_exllama": true

Issue - State: closed - Opened by XavierSpycy 9 months ago - 2 comments

#30 - KeyError: 'qwen2' Successfully installed transformers-4.37.2 vllm

Issue - State: closed - Opened by sparkfax 9 months ago - 3 comments

#29 - Tokenizer size and embedding size mismatch

Issue - State: closed - Opened by ghost 9 months ago - 5 comments

#28 - Where are the provided GGUF files?

Issue - State: closed - Opened by hikame 9 months ago - 1 comment

#27 - 请问Qwen1.5在prompt和stop token上和1代有变化吗？

Issue - State: closed - Opened by mzh1996 9 months ago - 6 comments

#25 - 请删除这个issue

Issue - State: closed - Opened by thyywr759 9 months ago

#24 - 运行示例代码，出现如下提示，该怎么处理？

Issue - State: closed - Opened by Li-Lai 9 months ago - 3 comments

#23 - Failed to import transformers.models.qwen2.modeling_qwen2

Issue - State: closed - Opened by lhtpluto 9 months ago - 1 comment

#22 - Model is getting loaded very slow onto gpu

Issue - State: closed - Opened by Charan1111 9 months ago - 2 comments

#21 - 有没有计划开发30B左右模型

Issue - State: closed - Opened by geasyheart 9 months ago - 1 comment

#19 - tokenizer应该使用AutoTokenizer还是Qwen2TokenizerFast呢

Issue - State: closed - Opened by Satan012 9 months ago - 1 comment

#18 - Qwen1.5-7B-Chat 最佳学习实践教程~

Issue - State: closed - Opened by KMnO4-zx 9 months ago - 2 comments

#17 - 千问1.5-api以及显存问题

Issue - State: closed - Opened by bimver 9 months ago - 6 comments

#16 - vllm deploy failed

Issue - State: closed - Opened by wxz1996 9 months ago - 3 comments

#13 - 安官网公开的quick start 报错 模型加载正常，生成报错

Issue - State: closed - Opened by hopeforus 9 months ago - 9 comments

#10 - 请问：72B模型量化后，和7B/14B模型对比，效果怎么样呢？

Issue - State: closed - Opened by ybdesire 9 months ago - 3 comments

#9 - Who knows what GQA and SWA refer to?

Issue - State: closed - Opened by zhujinchong 9 months ago - 1 comment

#7 - chat 模型不再提供chat方法了么？

Issue - State: closed - Opened by deathxlent 9 months ago - 9 comments

#6 - add README about function calling

Pull Request - State: closed - Opened by JianxinMa 9 months ago

#4 - finetune模型时支持最大的token数量是多少呢？

Issue - State: closed - Opened by hellozgm 9 months ago - 1 comment

#3 - docker镜像麻烦跟进更新一下谢谢

Issue - State: closed - Opened by Past-Tang 9 months ago - 2 comments

#2 - Definitely worth 10k stars!!!

Issue - State: closed - Opened by TobiasLee 10 months ago - 1 comment

#1 - Update README.md

Pull Request - State: closed - Opened by JustinLin610 10 months ago