CogVLM
CogVLM copied to clipboard
THUDM
a state-of-the-art-level open visual language model | 多模态预训练模型
Could you please provide the script for fine-tuning CogAgent with mind2web and AITW datasets?
### System Info / 系統信息 When I try to fine tune cogVLM in the demo script i set train and eval dataset but i not find where i can set...
### Feature request / 功能建议 如题 ### Motivation / 动机 如题 ### Your contribution / 您的贡献 如题
python cli_demo_sat.py --from_pretrained cogagent-chat --version chat --bf16 --stream_chat [2024-11-28 05:54:25,880] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) Traceback (most recent call last): File "/workspace/kkkjr/Item/CogVLM/basic_demo/cli_demo_sat.py", line 12, in from utils.utils...
No matter what the input is, the output is always very short and is bad at answering the question. For example, when the query is 'what is in this image?'...
### System Info / 系統信息 你好请问能自动化的使用微信 给对应人发送消息吗 ### Who can help? / 谁可以帮助到您？ _No response_ ### Information / 问题信息 - [ ] The official example scripts / 官方的示例脚本 - [...
Was extracting over 1000 images and wanted to summarise in each image was a unique person with age, gender, ethnicity, emotional tone. So with those 1000 images, Time for setting...
