Skip to content

Issues: THUDM/CogVLM2

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

44 Open 118 Closed
44 Open 118 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

CogVLM grounding training data
#187 opened Sep 2, 2024 by Michael4933
Is there a plan to release the TQA dataset used to train CogVLM2-Video?
#186 opened Sep 2, 2024 by peiliu0408
3
输入的图片尺寸过大，微调后的结果会有什么影响？
#185 opened Aug 29, 2024 by WuChannn
finetune，TypeError: jit() got an unexpected keyword argument 'debug'
#184 opened Aug 27, 2024 by Fu-ffion
2 tasks
您好，请问我该如何在CogVLM2-video-chat中设置system message
#183 opened Aug 22, 2024 by ShbGao-ProMax
2 tasks
1
为了方便cogvlm2技术交流，拉了一个多模态大模型技术交流群，有需要的大家可以加入
#182 opened Aug 22, 2024 by feihuamantian
TypeError: GenerationMixin._extract_past_from_model_output() got an unexpected keyword argument 'standardize_cache_format with transformers==4.44.0
#181 opened Aug 16, 2024 by 7801943
1 of 2 tasks
@zRzRzRzRzRzRzR
1
是否支持全参微调？
#180 opened Aug 15, 2024 by WuChannn
@zRzRzRzRzRzRzR
2
两张A100（共80G显存）测试openai_api_demo.py时报错OOM
#179 opened Aug 7, 2024 by thu-yn
@zRzRzRzRzRzRzR
2
当我在用A100运行微调代码的时候，出现torch.distributed.DistBackendError: NCCL error in: ../torch/csrc/distributed/c10d/ProcessGroupNCCL.cpp:1691, unhandled system error (run with NCCL_DEBUG=INFO for details), NCCL version 2.19.3 ncclSystemError: System call (e.g. socket, malloc) or external library call failed or device error.
#178 opened Aug 1, 2024 by 2279072142
1 of 2 tasks
使用TGI推理cogvlm2，url调用报错
#174 opened Jul 29, 2024 by ZZZ1223
@zRzRzRzRzRzRzR
About the release of temporal question-answering datasets
#173 opened Jul 27, 2024 by ruili33
We are making CogVLM 2 work on Windows with disabling Triton but it is working very slow can you help with code?
#172 opened Jul 26, 2024 by FurkanGozukara
basic_demo/cli_demo.py _issue
#171 opened Jul 26, 2024 by pangye202264690373
1 of 2 tasks
7
Please remove triton dependency for Windows users
#169 opened Jul 26, 2024 by FurkanGozukara
5
CogVLM2_grounding 近期有训练或发布的打算吗
#168 opened Jul 25, 2024 by qinzhenyi1314
@zRzRzRzRzRzRzR
1
question in Visual Grounding, what format of the region should i give?
#164 opened Jul 23, 2024 by LokiXun
CogVLM2-Video 多卡推理支持
#162 opened Jul 22, 2024 by zhengxingmao
@zRzRzRzRzRzRzR
3
cannot understand using Meta-Llama-3-8B-Instruct as base model
#161 opened Jul 22, 2024 by dreaming12580
1
tgi inference provides incomplete information
#158 opened Jul 20, 2024 by allendred
CogVLM2-Video web demo
#155 opened Jul 17, 2024 by Cherryjingyao
@zRzRzRzRzRzRzR
3
win10 support
#154 opened Jul 17, 2024 by sipie800
@zRzRzRzRzRzRzR
4
cogvlm2 official demo
#150 opened Jul 15, 2024 by wsxwd
@zRzRzRzRzRzRzR
3
模型不能输出attention吗
#149 opened Jul 14, 2024 by codemaker-123
@zRzRzRzRzRzRzR
1
CogVLM2 Videos demo
#144 opened Jul 11, 2024 by josephzpng
1 of 2 tasks
@zRzRzRzRzRzRzR
10
ProTip! Mix and match filters to narrow down what you’re looking for.