Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
THUDM
/
chatglm-6b-int4
like
417
Follow
Knowledge Engineering Group (KEG) & Data Mining at Tsinghua University
1.34k
Transformers
PyTorch
Chinese
English
chatglm
glm
thudm
custom_code
Inference Endpoints
arxiv:
2406.12793
Model card
Files
Files and versions
Community
21
Train
Deploy
Use this model
dac03c3
chatglm-6b-int4
6 contributors
History:
7 commits
DrSong
Fix bugs in quantization when loading kernels
dac03c3
over 1 year ago
.gitattributes
Safe
1.48 kB
initial commit
over 1 year ago
LICENSE
Safe
11.3 kB
init commmit
over 1 year ago
MODEL_LICENSE
Safe
2.35 kB
init commmit
over 1 year ago
README.md
Safe
4.67 kB
Update README.md
over 1 year ago
config.json
Safe
758 Bytes
init commmit
over 1 year ago
configuration_chatglm.py
Safe
4.06 kB
init commmit
over 1 year ago
ice_text.model
Safe
2.7 MB
LFS
init commmit
over 1 year ago
modeling_chatglm.py
Safe
52.5 kB
Fix Chinese punctuation
over 1 year ago
pytorch_model.bin
Safe
pickle
Detected Pickle imports (5)
"torch.FloatStorage"
,
"collections.OrderedDict"
,
"torch.HalfStorage"
,
"torch.CharStorage"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
4.06 GB
LFS
init commmit
over 1 year ago
quantization.py
Safe
28.8 kB
Fix bugs in quantization when loading kernels
over 1 year ago
quantization_kernels.c
Safe
1.16 kB
init commmit
over 1 year ago
quantization_kernels_parallel.c
Safe
1.61 kB
init commmit
over 1 year ago
tokenization_chatglm.py
Safe
12.5 kB
init commmit
over 1 year ago
tokenizer_config.json
Safe
416 Bytes
init commmit
over 1 year ago