Merge branch 'main' into attention
29038ea
duzx16
commited on
Commit History
Add support for flash attention 2
a7eaddd
duzx16
commited on
Merge branch 'main' of https://huggingface.co/THUDM/glm-4-9b-chat
1c2a801
duzx16
commited on
Add output_attentions for ChatGLMForSequenceClassification
f07eca1
duzx16
commited on
fix convert_tokens_to_string
547dc25
zR
commited on
fix readme
1b77b8d
zR
commited on
fix bug of config
5e8eeb1
zR
commited on
add chat_template (#31)
7375a2b
verified
Update apply_chat_template
d493e51
duzx16
commited on
Add eager and sdpa attention implementations
835c717
duzx16
commited on
Merge branch 'main' of https://huggingface.co/THUDM/glm-4-9b-chat
dba7772
duzx16
commited on
Fix default dtype for classification head
0deb1dd
duzx16
commited on
Update tokenization_chatglm.py (#7)
75792d7
verified
disable `torch.jit` when using Ascend NPUs (#20)
7d93f12
verified
Update LICENSE
6f060dc
verified
Update README.md (#26)
c938f44
verified
Fix classification model
12c8049
duzx16
commited on
readme
cbc9aaf
Ubuntu
commited on
english readme
368f865
Ubuntu
commited on
Update README.md
269b8ba
verified
8dc9e30
verified
fixes https://github.com/THUDM/GLM-4/issues/22 (#5)
0891486
verified
Update README.md
6324425
verified
Update README.md
b84dc74
verified
Update README.md
3caf9b5
verified
first commit
4b556ad
Ubuntu
commited on