Skip to content

Issues: THUDM/ChatGLM3

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

25 Open 758 Closed
25 Open 758 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

vllm==0.5.5orvllm==0.4.2都安转不上
#1336 opened Nov 13, 2024 by 18595071403
2 tasks done
请问用什么工具可以INT4 量化 ChatGLM3-6B这个模型？
#1334 opened Nov 7, 2024 by shawn9977
2 tasks
请问：ChatGLM3如何转成llama格式？
#1330 opened Oct 28, 2024 by avBuffer
手动调用mode()方法和直接调用model.generate()方法，输出的结果十分不同
#1328 opened Oct 17, 2024 by rooikeee
1 of 2 tasks
服务器部署chatglm3模型后，用postman开两个窗口几乎同时调用/v1/chat/completions这个接口（流式输出），最后回答的文本时看不懂的文字，如下图，平时问答是几秒，现在响应时间持续几十秒，输出的都是看不懂的文字
#1327 opened Oct 16, 2024 by levorge
TypeError: ChatGLMTokenizer._pad() got an unexpected keyword argument 'padding_side'
#1324 opened Sep 26, 2024 by jeejeelee
1 of 2 tasks
1
@zRzRzRzRzRzRzR
20
8G显存运行 basic_demo 加载到29%退出，无报错
#1323 opened Sep 25, 2024 by nick-bai
2 tasks
@zRzRzRzRzRzRzR
2
TypeError: GenerationMixin._extract_past_from_model_output() got an unexpected keyword argument 'standardize_cache_format'
#1321 opened Sep 15, 2024 by zhoujiaxinii
1 of 2 tasks
@zRzRzRzRzRzRzR
2
openai_api_request.py请求超时
#1314 opened Aug 21, 2024 by nightISend
1 task
@zRzRzRzRzRzRzR
使用ptuning_v2微调过程中出现报错ValueError: Hypothesis is empty.
#1312 opened Aug 17, 2024 by Lky0312
1 of 2 tasks
@zRzRzRzRzRzRzR
tools_using_demo中的openai_api_demo.py，stream等于True的时候 finish_reason 不出现"function_call"
#1311 opened Aug 15, 2024 by guolushi-7
1 of 2 tasks
@zRzRzRzRzRzRzR
1
The figure in execute function will be valued as None
#1310 opened Aug 13, 2024 by Stephen-SMJ
1 of 2 tasks
@zRzRzRzRzRzRzR
在ChatGLM3-6B的微调过程中，遇到如下报错（The following error occurs during the fine-tuning of ChatGLM3-6B)ImportError: cannot import name 'log' from 'torch.distributed.elastic.agent.server.api'
#1308 opened Aug 5, 2024 by Scorponok31
@zRzRzRzRzRzRzR
ModuleNotFoundError: No module named 'huggingface_hub.inference._text_generation'
#1307 opened Aug 5, 2024 by virtualpeer
2 tasks
@zRzRzRzRzRzRzR
3
requirements.txt冲突问题
#1304 opened Jul 31, 2024 by ZOUG
@zRzRzRzRzRzRzR
3
Intel demo AutoModelForCausalLM model.generate Wrong response by docker run the same chatglm3-int4 model bin file
#1302 opened Jul 29, 2024 by ahlwjnj
2 tasks done
AttributeError: 'GenerationConfig' object has no attribute '_eos_token_tensor'
#1299 opened Jul 26, 2024 by zzlTim
1 of 2 tasks
3
chatglm3-6b流式请求返回结果时，第一行会自带换行符
#1297 opened Jul 23, 2024 by starage2020
@zRzRzRzRzRzRzR
1
chatglm3-6b-32k处理长文本时，out of memory
#1294 opened Jul 21, 2024 by SXxinxiaosong
1 of 2 tasks
@zRzRzRzRzRzRzR
1
第一次尝试 github 中 lora_finetune.ipynb 微调示例，未执行成功，报以下错误，请问如何解决？
#1277 opened Jun 24, 2024 by thomasyyang
1 of 2 tasks
@zRzRzRzRzRzRzR
1
After update latest,The output is not accurate enough.
#1275 opened Jun 21, 2024 by haowaiwai
@zRzRzRzRzRzRzR
Getting requirements to build wheel did not run successfully.
#1259 opened Jun 6, 2024 by therobot1
1 of 2 tasks
@zRzRzRzRzRzRzR
1
ChatGLMForConditionalGeneration forward position_ids 参数哪里传入的？
#1255 opened Jun 4, 2024 by cqray1990
2 tasks done
@zRzRzRzRzRzRzR
RMSNorm的不同实现方式
#1240 opened May 28, 2024 by trundleyrg
1 of 2 tasks
@zRzRzRzRzRzRzR
这些问题不要在Issue提出，在Discussion中提出 duplicate This issue or pull request already exists enhancement New feature or request help wanted Extra attention is needed question Further information is requested wontfix This will not be worked on
#394 opened Nov 21, 2023 by zRzRzRzRzRzRzR 2.0 仓库持续维护阶段
@zRzRzRzRzRzRzR
26
ProTip! Add no:assignee to see everything that’s not assigned.