ZhipuAI-THUDM-Space

THUDM-Space's activity

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

New activity in THUDM/glm-4-9b about 2 months ago

How to use glm-4-9b to do classification?

1

#5 opened 9 months ago by

JustTryTry

可以出个gguf的版本吗？想本地部署测试

3

#6 opened 9 months ago by

nardoo

推理代码报错 ValueError: too many values to unpack (expected 2)

4

#9 opened 9 months ago by

qth-szu

TypeError: ChatGLM4Tokenizer._pad() got an unexpected keyword argument 'padding_side'

2

#16 opened 5 months ago by

TracyMc

New activity in THUDM/glm-4v-9b about 2 months ago

关于模型架构glm-4b-9b

1

#41 opened 4 months ago by

shinexuan

How to use EVA2CLIPModel directly for image embedding?

2

#38 opened 5 months ago by

yushan03

glm-4v-plus会有近期开源的打算吗？

1

#34 opened 7 months ago by

dibmvt

A100爆显存

3

#28 opened 9 months ago by

baiall

glm-4v-9b自己call forward的时候cuda out of memory

13

#25 opened 9 months ago by

FearandDreams

脚本貌似跑不起来，会报错

7

#5 opened 10 months ago by

haonanzhang

New activity in THUDM/glm-4-9b-chat 3 months ago

Converting to native Transformers

22

#81 opened 6 months ago by

cyrilvallez

适配新版transformers | adapt transformers update (https://github.com/huggingface/transformers/pull/31116)

2

#58 opened 9 months ago by

HibernantBear

Harness Evaluation

2

#56 opened 9 months ago by

VityaVitalich

Why GLM3 is better than GLM4 on LVEval benchmark?

1

#48 opened 9 months ago by

AnaRhisT

What's the chat prompt in plain string?

3

#59 opened 9 months ago by

apepkuss79

del gradient_checkpointing_enable()

1

#60 opened 8 months ago by

chandler88

qunatizer部分的为什么去掉了？

4

#10 opened 10 months ago by

fukai

New activity in THUDM/CogVideoX1.5-5B-I2V 3 months ago

AttributeError: 'CogVideoXTransformer3DModel' object has no attribute 'ofs_embedding'. Did you mean: 'time_embedding'?

18

#3 opened 4 months ago by

froilo

New activity in THUDM/CogVideoX-5B-Space 4 months ago

In love with your model!

3

#27 opened 4 months ago by

SashaAlexandra

New activity in THUDM/CogVideoX1.5-5B-I2V 4 months ago

Any optimization ways to accelerate the speed of inference

8

#7 opened 4 months ago by

mayukitan