Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
meituan
/
DeepSeek-R1-Block-INT8
like
44
Follow
meituan
125
Text Generation
Transformers
Safetensors
deepseek_v3
conversational
custom_code
text-generation-inference
8-bit precision
blockwise_int8
arxiv:
2501.12948
License:
mit
Model card
Files
Files and versions
Community
21
Train
Deploy
Use this model
main
DeepSeek-R1-Block-INT8
Commit History
Update README.md (
#10
)
e60c1b5
verified
pkumc
yuanzu
commited on
Feb 27
Update README.md (
#8
)
1842c56
verified
pkumc
HandH1998
commited on
Feb 25
Update inference/bf16_cast_block_int8.py (
#7
)
d476539
verified
pkumc
HandH1998
commited on
Feb 25
Update README.md (
#6
)
e48a514
verified
pkumc
yuanzu
commited on
Feb 24
Update README.md (
#5
)
160722a
verified
pkumc
yuanzu
commited on
Feb 24
Update README.md (
#3
)
d4440e1
verified
pkumc
yuanzu
commited on
Feb 24
Update README.md (
#2
)
c0b1d45
verified
pkumc
yuanzu
commited on
Feb 24
Update README.md (
#1
)
277034a
verified
pkumc
yuanzu
commited on
Feb 24
Add files using upload-large-folder tool
0d7d596
verified
pkumc
commited on
Feb 24
Add files using upload-large-folder tool
9a88c3a
verified
pkumc
commited on
Feb 24
Add files using upload-large-folder tool
98bd0fb
verified
pkumc
commited on
Feb 24
Add files using upload-large-folder tool
7d69425
verified
pkumc
commited on
Feb 24
Add files using upload-large-folder tool
8e8c28e
verified
pkumc
commited on
Feb 24
initial commit
ebeffaa
verified
pkumc
commited on
Feb 24