Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
jackaduma
/
Baichuan2-7B-Chat-8bits
like
0
Text Generation
Transformers
PyTorch
Chinese
English
baichuan
custom_code
text-generation-inference
8-bit precision
bitsandbytes
arxiv:
1910.07467
arxiv:
2009.03300
License:
mit
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
Baichuan2-7B-Chat-8bits
1 contributor
History:
8 commits
jackaduma
Update README.md
08d5e4a
about 1 year ago
.gitattributes
1.52 kB
initial commit
about 1 year ago
README.md
12.7 kB
Update README.md
about 1 year ago
added_tokens.json
22 Bytes
Upload 11 files
about 1 year ago
config.json
1.19 kB
Upload 11 files
about 1 year ago
configuration_baichuan.py
2.45 kB
Upload 11 files
about 1 year ago
generation_config.json
285 Bytes
Upload 11 files
about 1 year ago
generation_utils.py
2.97 kB
Upload 11 files
about 1 year ago
modeling_baichuan.py
33.2 kB
Upload 11 files
about 1 year ago
pytorch_model.bin
pickle
Detected Pickle imports (4)
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.HalfStorage"
,
"torch.CharStorage"
What is a pickle import?
8.54 GB
LFS
Upload pytorch_model.bin
about 1 year ago
quantizer.py
9.07 kB
Upload 11 files
about 1 year ago
special_tokens_map.json
548 Bytes
Upload 11 files
about 1 year ago
tokenization_baichuan.py
9.61 kB
Upload 11 files
about 1 year ago
tokenizer.model
2 MB
LFS
Upload 11 files
about 1 year ago
tokenizer_config.json
795 Bytes
Upload 11 files
about 1 year ago