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

56 Open 120 Closed
56 Open 120 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

如何指定多张GPU卡跑，默认用一张，显示GPU内存不够
#208 opened Dec 26, 2024 by sf9ehf9fe
1 of 2 tasks
ImportError: /home/root/anaconda/envs/cogvlm2/lib/python3.10/site-packages/torch/lib/../../nvidia/cusparse/lib/libcusparse.so.12: symbol __nvJitLinkComplete_12_4, version libnvJitLink.so.12 not defined in file libnvJitLink.so.12 with link time reference
#207 opened Dec 26, 2024 by sf9ehf9fe
1 of 2 tasks
1
如何部署环境
#206 opened Dec 26, 2024 by sf9ehf9fe
2 tasks done
1
视频描述大量出现”watermark“和”bilibili“
#205 opened Dec 23, 2024 by ZXMMD
1
TypeError: _extract_past_from_model_output() got an unexpected keyword argument 'standardize_cache_format'
#204 opened Dec 16, 2024 by sjghh
1 of 2 tasks
请问如何拿几张图片做fewshot
#203 opened Dec 2, 2024 by Nand-Lu
2 tasks
用xinference在jetson agx orin上部署cogvlm2模型后，模型可以加载但是无法进行对话，报[address=0.0.0.0:38925, pid=1624735] object of type 'NoneType' has no len()
#202 opened Nov 12, 2024 by GengyuXu
1 of 2 tasks
Fine tune for detection
#201 opened Nov 12, 2024 by ck-amrahd
cogvlm2-video chat模式如何更改语言模型到Qwen2.5
#199 opened Oct 28, 2024 by zhengxingmao
论文中提到的对齐数据会开源吗
#197 opened Oct 17, 2024 by ZhangLin009
Question about Caption Model
#195 opened Oct 15, 2024 by zhiyuanyou
1
Question about expert_mask
#194 opened Oct 14, 2024 by xiaojunjie
1 of 2 tasks
1
finetune cogvlm2-video
#192 opened Sep 29, 2024 by yepzhang
3
Question about face-specific action analysis in video input
#189 opened Sep 10, 2024 by YoungjaeDev
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
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
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
2
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
ProTip! Mix and match filters to narrow down what you’re looking for.