Hugging Face's logo

Z.ai & THUKEG

Enterprise
university
https://github.com/THUDM
thukeg
THUDM
Activity Feed

AI & ML interests

AGI, LLMs, ChatGLM

Recent Activity

bys0318  authored a paper 2 days ago
An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes
zRzRzRzRzRzRzR  new activity 2 days ago
THUDM/GLM-4-32B-0414:What's the max context on this?
zRzRzRzRzRzRzR  updated a model 2 days ago
THUDM/glm-4-9b
View all activity

THUDM's activity

bys0318 
authored a paper 2 days ago
zRzRzRzRzRzRzR 
in THUDM/GLM-4-32B-0414 2 days ago

What's the max context on this?

1
#9 opened 3 days ago by
ThePabli
zRzRzRzRzRzRzR 
updated a model 2 days ago
hrw 
published 2 models 2 days ago
hrw 
published a dataset 2 days ago
hrw 
updated a dataset 2 days ago
hrw 
updated 3 models 2 days ago
think2try 
updated a model 2 days ago
zRzRzRzRzRzRzR 
in THUDM/GLM-4-32B-0414 5 days ago

When running with a single GPU, I get an error saying the VRAM is insufficient. However, when using multiple GPUs on a single machine, there are many errors. My vllm version is 0.8.4.

1
#6 opened 6 days ago by
hanson888
zRzRzRzRzRzRzR 
in THUDM/GLM-4-32B-0414 7 days ago

Some bug when using function call with vllm==0.8.4

2
#4 opened 7 days ago by
waple
zRzRzRzRzRzRzR 
in THUDM/GLM-4-9B-0414 7 days ago

I get too many repetitions

6
#5 opened 9 days ago by
JLouisBiz
zRzRzRzRzRzRzR 
in THUDM/GLM-4-9B-0414 8 days ago

Readme information missing for this non-reasoning model

2
#4 opened 9 days ago by
Doctor-Chad-PhD

When will the GLM-4/Z1 series model support VLLM?

2
#6 opened 8 days ago by
David3698
zRzRzRzRzRzRzR 
in THUDM/GLM-Z1-9B-0414 9 days ago

fail to load BLM-Z1-9B DUE TO tokenization ISSUE

4
#1 opened 9 days ago by
Fleinstein
zRzRzRzRzRzRzR 
in THUDM/GLM-Z1-Rumination-32B-0414 9 days ago

bug in demo code

2
#2 opened 9 days ago by
undefined-x
zRzRzRzRzRzRzR 
updated a model 9 days ago
zRzRzRzRzRzRzR 
in THUDM/GLM-4-9B-0414 10 days ago

Base model

2
#1 opened 10 days ago by
mrfakename