THUDM/CogVLM2

Issues

• 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 a month ago by GengyuXu
  0

• Fine tune for detection

  #201 opened a month ago by ck-amrahd
  0

• cogvlm2-video chat模式如何更改语言模型到Qwen2.5

  #199 opened 2 months ago by zhengxingmao
  0

• cogvlm2-video chat模式如何更改推理的帧数？

  #196 opened 2 months ago by zhengxingmao
  3

• 论文中提到的对齐数据会开源吗

  #197 opened 2 months ago by ZhangLin009
  0

• Question about Caption Model

  #195 opened 2 months ago by zhiyuanyou
  1

• Question about expert_mask

  #194 opened 2 months ago by xiaojunjie
  0

• 使用web_demo输入图片时报错

  #193 opened 2 months ago by Leox0717
  0

• TypeError: GenerationMixin._extract_past_from_model_output() got an unexpected keyword argument 'standardize_cache_format with transformers==4.44.0

  #181 opened 4 months ago by 7801943
  2

• finetune cogvlm2-video

  #192 opened 3 months ago by yepzhang
  1

• 构建了一个【MLLM多模态】学习交流群

  #190 opened 3 months ago by km1994
  0

• Question about face-specific action analysis in video input

  #189 opened 3 months ago by YoungjaeDev
  0

• finetune，TypeError: jit() got an unexpected keyword argument 'debug'

  #184 opened 4 months ago by Fu-ffion
  1

• Failure in loading QUANT4 model

  #188 opened 4 months ago by lisb20
  1

• Is there a plan to release the TQA dataset used to train CogVLM2-Video?

  #186 opened 4 months ago by peiliu0408
  3

• CogVLM grounding training data

  #187 opened 4 months ago 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 4 months ago by WuChannn
  0

• 您好，请问我该如何在CogVLM2-video-chat中设置system message

  #183 opened 4 months ago by ShbGao-ProMax
  1

• 是否支持全参微调？

  #180 opened 4 months ago by WuChannn
  2

• raise RuntimeError("No GPU found. A GPU is needed for quantization.")

  #177 opened 4 months ago by gg22mm
  1

• CogVLM2_grounding 近期有训练或发布的打算吗

  #168 opened 5 months ago by qinzhenyi1314
  1

• 使用TGI推理cogvlm2，url调用报错

  #174 opened 5 months ago by ZZZ1223
  0

• 两张A100（共80G显存）测试openai_api_demo.py时报错OOM

  #179 opened 5 months ago by thu-yn
  2

• 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 5 months ago by Celine-hxy
  3

• basic_demo/cli_demo.py _issue

  #171 opened 5 months ago by pangye202264690373
  7

• 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 5 months ago by 2279072142
  0

• Path error multi gpu in WSL2

  #165 opened 5 months ago by michale-ai
  0

• Please remove triton dependency for Windows users

  #169 opened 5 months ago by FurkanGozukara
  5

• RuntimeError

  #159 opened 5 months ago by chenzhe-PKID
  2

• We are making CogVLM 2 work on Windows with disabling Triton but it is working very slow can you help with code?

  #172 opened 5 months ago by FurkanGozukara
  0

• About the release of temporal question-answering datasets

  #173 opened 5 months ago by ruili33
  0

• ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'

  #141 opened 5 months ago by Sumail2020
  3

• cogvlm2 official demo

  #150 opened 5 months ago by wsxwd
  3

• cli_demo.py is broken tested on ubuntu pip freeze included - AttributeError: 'str' object has no attribute 'shape'

  #170 opened 5 months ago by FurkanGozukara
  2

• win10 support

  #154 opened 5 months ago by sipie800
  4

• cannot understand using Meta-Llama-3-8B-Instruct as base model

  #161 opened 5 months ago by dreaming12580
  1

• CogVLM2-Video 多卡推理支持

  #162 opened 5 months ago by zhengxingmao
  3

• Minimum finetuning dataset size

  #163 opened 5 months ago by pranavatreya
  2

• question in Visual Grounding, what format of the region should i give?

  #164 opened 5 months ago by LokiXun
  0

• CogVLM2 Videos demo

  #144 opened 5 months ago by josephzpng
  10

• tgi inference provides incomplete information

  #158 opened 5 months ago by allendred
  0

• 模型推理时始终出现错误

  #157 opened 5 months ago by htesd
  1

• CogVLM2-Video web demo

  #155 opened 5 months ago by Cherryjingyao
  3

• Fail to run a demo

  #156 opened 5 months ago by avalonliberty
  2

• cogvlm2-llama3-chinese-chat-19B-int4, 使用CLI demo，输出报错

  #145 opened 5 months ago 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 5 months ago by kaka-Cao
  1

• 模型不能输出attention吗

  #149 opened 5 months ago by codemaker-123
  1

• 基于 CogVLM2 的 CogAgent 有开发计划和预期推出时间吗？

  #152 opened 5 months ago by RYWei
  1

• 多图或者interleave图文

  #147 opened 5 months ago by pennypengpm
  1

• transformers-4.42.3 无法运行basic demo，4.41.3可以正常运行basic demo

  #142 opened 5 months ago by Sumail2020
  1