THUDM
/

cogvlm-chat-hf

Text Generation

Model card Files Files and versions Community

Resources

View closed (14)

Increasing throughput with batches and quantization

#11 opened about 1 year ago by

new dependencies

#23 opened 5 days ago by

Torchvision error

#22 opened 4 months ago by

Breaks with quantization in newer transformers revisions (fix included)

#21 opened 11 months ago by

Update modeling_cogvlm.py

#19 opened 12 months ago by

How to Encode Inputs for Supervised Fine-tuning of CogVLM

#17 opened about 1 year ago by

noob: Can we use RAG to improve cogagent/cogvlm performance

#16 opened about 1 year ago by

Stunningly good

#13 opened about 1 year ago by

Guidance on How to Train / Finetune Model

#6 opened about 1 year ago by