Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
stable-code-3b-GPTQ
like
12
Text Generation
Transformers
Safetensors
6 datasets
English
stablelm_epoch
causal-lm
code
custom_code
Eval Results
4-bit precision
gptq
arxiv:
7 papers
License:
other
Model card
Files
Files and versions
Community
2
Train
Use this model
main
stable-code-3b-GPTQ
/
quantize_config.json
TheBloke
GPTQ model commit
eb634be
verified
10 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
133 Bytes
{
"bits"
:
4
,
"group_size"
:
128
,
"damp_percent"
:
0.1
,
"desc_act"
:
true
,
"sym"
:
true
,
"true_sequential"
:
true
}