Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
THUDM
/
chatglm-6b-int8
like
71
Follow
Knowledge Engineering Group (KEG) & Data Mining at Tsinghua University
1.45k
Transformers
PyTorch
Chinese
English
chatglm
glm
thudm
custom_code
Inference Endpoints
arxiv:
2406.12793
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
refs/pr/2
chatglm-6b-int8
2 contributors
History:
16 commits
SFconvertbot
Adding `safetensors` variant of this model
5d03d21
verified
10 days ago
.gitattributes
1.48 kB
initial commit
over 1 year ago
LICENSE
11.3 kB
Init commit
over 1 year ago
MODEL_LICENSE
2.35 kB
Init commit
over 1 year ago
README.md
5.61 kB
Update README.md
5 months ago
config.json
838 Bytes
Init commit
over 1 year ago
configuration_chatglm.py
4.38 kB
Init commit
over 1 year ago
ice_text.model
2.71 MB
LFS
Upload ice_text.model
over 1 year ago
model.safetensors
6.71 GB
LFS
Adding `safetensors` variant of this model
10 days ago
modeling_chatglm.py
59.4 kB
Sync with chatglm-6b
over 1 year ago
pytorch_model.bin
pickle
Detected Pickle imports (4)
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.CharStorage"
,
"torch.HalfStorage"
What is a pickle import?
6.71 GB
LFS
Upload pytorch_model.bin
over 1 year ago
quantization.py
31 kB
Add support for parallel quantization on Mac
over 1 year ago
quantization_kernels.c
1.16 kB
Init commit
over 1 year ago
quantization_kernels_parallel.c
1.61 kB
Init commit
over 1 year ago
tokenization_chatglm.py
17 kB
Update decode method in tokenizer
over 1 year ago
tokenizer_config.json
446 Bytes
Init commit
over 1 year ago
