Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
meituan
/
DeepSeek-R1-Block-INT8
like
33
Follow
meituan
99
Text Generation
Transformers
Safetensors
deepseek_v3
conversational
custom_code
8-bit precision
blockwise_int8
arxiv:
2501.12948
License:
mit
Model card
Files
Files and versions
Community
18
Train
Use this model
Update inference/bf16_cast_block_int8.py
#7
by
HandH1998
- opened
18 days ago
base:
refs/heads/main
←
from:
refs/pr/7
Discussion
Files changed
+30
-5
HandH1998
18 days ago
update bf16_cast_block_int8.py for easy usage
See translation
Update inference/bf16_cast_block_int8.py
ca686702
pkumc
changed pull request status to
merged
18 days ago
Edit
Preview
Upload images, audio, and videos by dragging in the text input, pasting, or
clicking here
.
Tap or paste here to upload images
Your need to confirm your account before you can post a new comment.
Comment
·
Sign up
or
log in
to comment
