THUDM
/

glm-10b-chinese

Feature Extraction

Model card Files Files and versions Community

Resources

View closed (2)

Bug Report

#10 opened 8 months ago by

How to solve Model inference speed is too slow？

#9 opened over 1 year ago by

求助AttributeError: 'GLMModel' object has no attribute 'stream_chat'

#8 opened over 1 year ago by

int4/8 quantization so that we can deploy on consumer-grid gpu card

#7 opened over 1 year ago by

Is this trained the same way as 6B model, and the only difference is the model size?

#6 opened over 1 year ago by

Cannot find mask token in the input 的错误

#4 opened over 1 year ago by

Support accelerate for GLM

#2 opened over 1 year ago by

RuntimeError: expected self and mask to be on the same device, but got mask on cpu and self on cuda:0

#1 opened over 1 year ago by