Keqin Chen

chenkq's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

New activity in THUDM/CogVLM 5 months ago

The files in the zip compression package seem to be different from the files named -hf, I would like to ask what is the difference between the two?

4

#5 opened 5 months ago by wkh666

New activity in THUDM/cogvlm-chat-hf 5 months ago

No such file or directory: 'ldconfig'

2

#10 opened 6 months ago by miguelcarv

NotImplementedError

1

#12 opened 6 months ago by Soraheart1988

Note to others trying to run this

10

#2 opened 6 months ago by lzxcgnkhnrlnto

Increasing throughput with batches and quantization

7

#11 opened 6 months ago by miguelcarv

Support for gradient checkpointing and Flash Attention

2

#14 opened 5 months ago by sidnb13

New activity in THUDM/cogvlm-chat-hf 6 months ago

How to run fp16?

1

#5 opened 6 months ago by grim3000

How to run inference using multiple GPUs

1

#9 opened 6 months ago by NancyQingQing

How to deploy this model on sage maker and use as a api

1

#7 opened 6 months ago by Imran1

batch input

1

#8 opened 6 months ago by ptx0

Error when dispatching model into multiple GPUs

6

#4 opened 6 months ago by justinwickett

Is the hf version the same as the biligual demo version in Chatglm.cn?

2

#1 opened 6 months ago by jaywanghz

Update modeling_cogvlm.py

#3 opened 6 months ago by ybelkada