THUDM
/

chatglm-6b-int4-qe

Feature Extraction

Model card Files Files and versions Community

chatglm-6b-int4-qe

Ctrl+K

Ctrl+K

2 contributors

History: 18 commits

duzx16

Fix eos token in tokenizer

5f775b8 about 2 years ago

.gitattributes

1.58 kB

Upload ChatGLM-6B-INT4-QE over 2 years ago
LICENSE.txt

11.3 kB

Upload ChatGLM-6B-INT4-QE over 2 years ago
MODEL_LICENSE.txt

2.35 kB

Upload ChatGLM-6B-INT4-QE over 2 years ago
README.md

4.67 kB

Update dependency about 2 years ago
config.json

859 Bytes

Slim embedding about 2 years ago
configuration_chatglm.py

4.38 kB

Slim embedding about 2 years ago
ice_text.model

2.71 MB
LFS

Drop icetk dependency about 2 years ago
modeling_chatglm.py

58.4 kB

Fix attention score on mps about 2 years ago
pytorch_model.bin
Detected Pickle imports (4)
- "collections.OrderedDict",
- "torch.HalfStorage",
- "torch._utils._rebuild_tensor_v2",
- "torch.CharStorage"
What is a pickle import?
3.36 GB
LFS

Upload pytorch_model.bin about 2 years ago
quantization.py

29 kB

Slim embedding about 2 years ago
quantization_kernels.c

1.16 kB

Upload ChatGLM-6B-INT4-QE over 2 years ago
quantization_kernels_parallel.c

1.61 kB

Fix parallel cpu kernel over 2 years ago
tokenization_chatglm.py

16.7 kB

Fix eos token in tokenizer about 2 years ago
tokenizer_config.json

441 Bytes

Fix eos token in tokenizer about 2 years ago