Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
localmodels
/
Vicuna-33B-v1.3-GPTQ
like
0
Follow
Local Models
38
Text Generation
Transformers
llama
Inference Endpoints
arxiv:
2302.13971
arxiv:
2306.05685
Model card
Files
Files and versions
Train
Deploy
Use this model
ae0003d
Vicuna-33B-v1.3-GPTQ
/
quantize_config.json
ukim4
Duplicate from localmodels/LLM
ae0003d
over 1 year ago
raw
Copy download link
history
blame
Safe
133 Bytes
{
"bits"
:
4
,
"group_size"
:
-1
,
"damp_percent"
:
0.01
,
"desc_act"
:
true
,
"sym"
:
true
,
"true_sequential"
:
true
}