Hugging Face's logo

THUDM
/
chatglm2-6b-int4

Transformers
PyTorch
Chinese
English
chatglm
glm
thudm
custom_code
Inference Endpoints
Model card Files Community
25
chatglm2-6b-int4

Commit History

Adding `safetensors` variant of this model
192828d
verified

SFconvertbot commited on

for transformers 4.47
a954550
verified

zRzRzRzRzRzRzR commited on

support transformers 4.47
548388c
verified

zRzRzRzRzRzRzR commited on

Update README.md
d93643f
verified

yuxiaod commited on

Update README.md
63d11d4
verified

yuxiaod commited on

Fix use_cache=False
66ecaf1

duzx16 commited on

Fix tokenizer for transformers 0.34
833de79

duzx16 commited on

Update use case
382cc70

duzx16 commited on

Update quantized gemm kernel
5579a9f

duzx16 commited on

Fix prefix projection
8049563

duzx16 commited on

Fix tokenization space
71189e7

duzx16 commited on

Add prefix prompt
eb3e683

duzx16 commited on

Update slack link
cdb65fd

duzx16 commited on

Add default model type
939776a

duzx16 commited on

Update modeling_chatglm.py
99564c0

duzx16 commited on

Add pad_token_id
ccb0160

duzx16 commited on

Fix arange_cpu
be192fb

duzx16 commited on

Update requirement
5b97c61

duzx16 commited on

Add cpu kernel
8b97bf2

duzx16 commited on

Merge branch 'main' of https://huggingface.co/THUDM/chatglm2-6b-int4
3cbefb1

duzx16 commited on

Init commit
8668ecb

duzx16 commited on

Upload tokenizer.model with huggingface_hub
8fa9b79

zxdu20 commited on

Upload pytorch_model.bin with huggingface_hub
aa7d1bd

zxdu20 commited on

initial commit
85dc392

zxdu20 commited on