Issues
- 0
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 by GengyuXu - 0
Fine tune for detection
#201 opened by ck-amrahd - 0
cogvlm2-video chat模式如何更改语言模型到Qwen2.5
#199 opened by zhengxingmao - 3
cogvlm2-video chat模式如何更改推理的帧数?
#196 opened by zhengxingmao - 0
论文中提到的对齐数据会开源吗
#197 opened by ZhangLin009 - 1
Question about Caption Model
#195 opened by zhiyuanyou - 0
Question about expert_mask
#194 opened by xiaojunjie - 0
使用web_demo输入图片时报错
#193 opened by Leox0717 - 2
TypeError: GenerationMixin._extract_past_from_model_output() got an unexpected keyword argument 'standardize_cache_format with transformers==4.44.0
#181 opened by 7801943 - 1
finetune cogvlm2-video
#192 opened by yepzhang - 0
构建了一个【MLLM多模态】学习交流群
#190 opened by km1994 - 0
- 1
- 1
Failure in loading QUANT4 model
#188 opened by lisb20 - 3
- 0
CogVLM grounding training data
#187 opened by Michael4933 - 0
输入的图片尺寸过大,微调后的结果会有什么影响?
#185 opened by WuChannn - 1
您好,请问我该如何在CogVLM2-video-chat中设置system message
#183 opened by ShbGao-ProMax - 2
- 1
- 1
CogVLM2_grounding 近期有训练或发布的打算吗
#168 opened by qinzhenyi1314 - 0
使用TGI推理cogvlm2,url调用报错
#174 opened by ZZZ1223 - 2
两张A100(共80G显存)测试openai_api_demo.py时报错OOM
#179 opened by thu-yn - 3
使用cogvlm2-video的CLI demo报错Exception has occurred: RuntimeError: view size is not compatible with input tensor's size and stride
#148 opened by Celine-hxy - 7
basic_demo/cli_demo.py _issue
#171 opened by pangye202264690373 - 0
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 by 2279072142 - 0
Path error multi gpu in WSL2
#165 opened by michale-ai - 5
- 2
RuntimeError
#159 opened by chenzhe-PKID - 0
We are making CogVLM 2 work on Windows with disabling Triton but it is working very slow can you help with code?
#172 opened by FurkanGozukara - 0
- 3
ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'
#141 opened by Sumail2020 - 3
cogvlm2 official demo
#150 opened by wsxwd - 2
cli_demo.py is broken tested on ubuntu pip freeze included - AttributeError: 'str' object has no attribute 'shape'
#170 opened by FurkanGozukara - 4
win10 support
#154 opened by sipie800 - 1
- 3
CogVLM2-Video 多卡推理支持
#162 opened by zhengxingmao - 2
Minimum finetuning dataset size
#163 opened by pranavatreya - 0
- 10
CogVLM2 Videos demo
#144 opened by josephzpng - 0
tgi inference provides incomplete information
#158 opened by allendred - 1
模型推理时始终出现错误
#157 opened by htesd - 3
CogVLM2-Video web demo
#155 opened by Cherryjingyao - 2
Fail to run a demo
#156 opened by avalonliberty - 1
cogvlm2-llama3-chinese-chat-19B-int4, 使用CLI demo,输出报错
#145 opened by tectal - 1
请问在cogvlm2模型上如何使用RLHF-V数据集进行DPO训练
#151 opened by kaka-Cao - 1
模型不能输出attention吗
#149 opened by codemaker-123 - 1
基于 CogVLM2 的 CogAgent 有开发计划和预期推出时间吗?
#152 opened by RYWei - 1
多图或者interleave图文
#147 opened by pennypengpm - 1