glm-4-9b-chat / modeling_chatglm.py

Commit History

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

89cf208
verified

HibernantBear commited on Jul 2, 2024

fix import error of flash attn

df6a8f3

zR commited on Jun 26, 2024

flash_attention_2 (#51)

10b3f35
verified

zxdu20 commited on Jun 24, 2024

Add output_attentions for ChatGLMForSequenceClassification

f07eca1

duzx16 commited on Jun 21, 2024

Merge branch 'main' of https://huggingface.co/THUDM/glm-4-9b-chat

dba7772

duzx16 commited on Jun 19, 2024

Fix default dtype for classification head

0deb1dd

duzx16 commited on Jun 19, 2024

disable `torch.jit` when using Ascend NPUs (#20)

7d93f12
verified

zRzRzRzRzRzRzR

statelesshz commited on Jun 13, 2024

Fix classification model

12c8049

duzx16 commited on Jun 6, 2024

fix tensor shape error when torch version less than 2 #4 (#9)

8dc9e30
verified

zRzRzRzRzRzRzR

hiyouga commited on Jun 5, 2024

fixes https://github.com/THUDM/GLM-4/issues/22 (#5)

0891486
verified

zRzRzRzRzRzRzR

hiyouga commited on Jun 5, 2024

first commit

4b556ad

Ubuntu commited on Jun 4, 2024

Commit History

适配新版transformers | adapt transformers update (https://github.com/huggingface/transformers/pull/31116) 89cf208 verified

fix import error of flash attn df6a8f3

flash_attention_2 (#51) 10b3f35 verified

Add output_attentions for ChatGLMForSequenceClassification f07eca1

Merge branch 'main' of https://huggingface.co/THUDM/glm-4-9b-chat dba7772

Fix default dtype for classification head 0deb1dd

disable `torch.jit` when using Ascend NPUs (#20) 7d93f12 verified

Fix classification model 12c8049

fix tensor shape error when torch version less than 2 #4 (#9) 8dc9e30 verified

fixes https://github.com/THUDM/GLM-4/issues/22 (#5) 0891486 verified

first commit 4b556ad

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

89cf208
verified

fix import error of flash attn

df6a8f3

flash_attention_2 (#51)

10b3f35
verified

Add output_attentions for ChatGLMForSequenceClassification

f07eca1

Merge branch 'main' of https://huggingface.co/THUDM/glm-4-9b-chat

dba7772

Fix default dtype for classification head

0deb1dd

disable `torch.jit` when using Ascend NPUs (#20)

7d93f12
verified

Fix classification model

12c8049

fix tensor shape error when torch version less than 2 #4 (#9)

8dc9e30
verified

fixes https://github.com/THUDM/GLM-4/issues/22 (#5)

0891486
verified

first commit

4b556ad