Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
compressa-ai
/
Llama-3-70B-Instruct-OmniQuant
like
0
Follow
Compressa
7
Text Generation
Transformers
Safetensors
llama
llama3
omniquant
gptq
triton
conversational
text-generation-inference
Inference Endpoints
4-bit precision
License:
llama3
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
1f3dc6b
Llama-3-70B-Instruct-OmniQuant
File size: 63 Bytes
1f3dc6b
1
{
"wbits"
:
4
,
"abits"
:
16
,
"group_size"
:
128
,
"symmetric"
:
true
}