THUDM / CogVLM2

GPT4V-level open-source multi-modal model based on Llama3-8B

THUDM/CogVLM2 Issues

basic_demo/cli_demo.py _issue
Updated 3 days ago2
Please remove triton dependency for Windows users
Updated 3 days ago5
使用TGI推理cogvlm2，url调用报错
Updated 4 days ago
RuntimeError
Closed 6 days ago2
We are making CogVLM 2 work on Windows with disabling Triton but it is working very slow can you help with code?
Updated 6 days ago
About the release of temporal question-answering datasets
Updated 6 days ago
ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'
Closed 22 days ago3
cogvlm2 official demo
Updated 7 days ago3
cli_demo.py is broken tested on ubuntu pip freeze included - AttributeError: 'str' object has no attribute 'shape'
Closed 7 days ago2
win10 support
Updated 7 days ago4
How do I change the task from chat to caption?
Updated 7 days ago1
CogVLM2_grounding 近期有训练或发布的打算吗
Updated 8 days ago
拉了一个多模态大模型技术交流群，大家可以加入进来进行技术交流
Closed 8 days ago
cannot understand using Meta-Llama-3-8B-Instruct as base model
Updated 9 days ago1
CogVLM2-Video 多卡推理支持
Updated 9 days ago3
Minimum finetuning dataset size
Closed 9 days ago2
Path error multi gpu in WSL2
Updated 10 days ago
question in Visual Grounding, what format of the region should i give?
Updated 10 days ago
CogVLM2 Videos demo
Updated 13 days ago10
tgi inference provides incomplete information
Updated 13 days ago
模型推理时始终出现错误
Closed 13 days ago1
【text-generation-inference】Unsupported model type cogvlm2
Closed 17 days ago3
CogVLM2-Video web demo
Updated 15 days ago3
Fail to run a demo
Closed 15 days ago2
cogvlm2-llama3-chinese-chat-19B-int4, 使用CLI demo，输出报错
Closed 17 days ago1
请问在cogvlm2模型上如何使用RLHF-V数据集进行DPO训练
Closed 17 days ago1
模型不能输出attention吗
Updated 17 days ago1
openai_api_demo.py on 2 nvidia 3090 GPU
Closed 17 days ago1
基于 CogVLM2 的 CogAgent 有开发计划和预期推出时间吗？
Closed 17 days ago1
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
Closed 17 days ago1
在做文档类图片要素提取任务时，无中生有现象严重
Closed 21 days ago5
How many GPU memory is required to inference CogVLM2 in float16
Closed 21 days ago5
多图或者interleave图文
Closed 21 days ago1
'str' object has no attribute 'shape' int4 model
Closed 23 days ago1
Problems running CogVLM2 on Google Colab Runtime T4
Updated 22 days ago2
transformers-4.42.3 无法运行basic demo，4.41.3可以正常运行basic demo
Closed 22 days ago1
在xinference推理时异常
Closed 22 days ago1
多显卡加载失败,在使用4张14.8G的显卡时,运行cli_demo_multi_gpus.py显存溢出
Closed 22 days ago2
Detailed Instructions for Installing CogVLM2 on Amazon Linux 2 or Google Colab
Updated 23 days ago
CogVLM-2Video 4-bit and 8-bit bugs and kind request for multi-gpu demo
Closed 23 days ago
微调glm-4v-9B时的lora-target应该写什么？
Closed 25 days ago6
bug
Closed a month ago2
referring expression comprehension support for CogVLM2
Updated a month ago1
cuda11.7 模型推理报错
Closed a month ago3
huggingface model how to convert to SAT model
Updated a month ago4
模型会有上下文的记忆功能吗？
Closed a month ago1
微调接口是否正确?用小批量数据微调5个epoch后模型完全没学到东西
Closed a month ago
File "/root/.cache/huggingface/modules/transformers_modules/cogvlm2-llama3-chinese-chat-19B-int4/modeling_cogvlm.py", line 387, in forward assert len(input_ids) == len(images), f"{len(input_ids)} {len(images)}" AssertionError: 2 1
Updated a month ago
如何进行单机多卡训练?
Closed a month ago
本地部署模型的输出与在线样例不一致, 本地效果较差且不稳定
Closed a month ago11