Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
yejingfu
/
q-Meta-Llama-3.1-8B-Instruct_w8a8
like
0
PyTorch
llama
License:
llama3.1
Model card
Files
Files and versions
Community
Train
main
q-Meta-Llama-3.1-8B-Instruct_w8a8
File size: 65 Bytes
a5f6fa3
1
2
3
4
5
{
"w_bit"
:
8
,
"version"
:
"MIX"
,
"q_group_size"
:
128
}