Repository Issue Activity (beta)

#219 run peft_infer.py and get TypeError: TextEncodeInput must be Union[TextInputSequence, Tuple[InputSequence, InputSequence]]

#218 AttributeError: 'CogVLMForCausalLM' object has no attribute '_extract_past_from_model_output'

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

#21 int4 cli_demo run

#217 如何对长视频进行理解

#215 文档写这么差，真的不考虑优化一下吗

#141 ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'

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

#205 视频描述大量出现”watermark“和”bilibili“

#206 如何部署环境

#214 Cogvlm2-llama3-chinese-chat-19B 不能多卡推理

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

#47 triton在windows不太好装，请问有其他推理版本吗？目前在windows跑cogvlm2-llama3-chinese-chat-19B-int4会报错

#216 线上测试demo不可用，

#204 TypeError: _extract_past_from_model_output() got an unexpected keyword argument 'standardize_cache_format'

#32 Multi-GPU inference Error: RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:5 and cuda:6!

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

#212 1-Click installers for Windows, RunPod, Massed Compute and ultra advanced CogVLM 2 Batch Processing Gradio APP with 4-bit quantization

#123 huggingface model how to convert to SAT model

#213 ValueError when adding “--quant 4” in running openai_api_demo.py

#210 单卡的T4,16G显存（实际显存15G可用）跑不了INT4，有什么办法能在单卡上跑起来吗

#211 指定多张GPU运行报AttributeError: 'Params4bit' object has no attribute '_parameters'

#133 Problems running CogVLM2 on Google Colab Runtime T4

#209 subprocess.CalledProcessError: Command

#208 如何指定多张GPU卡跑，默认用一张，显示GPU内存不够