Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
notstoic
/
pygmalion-13b-4bit-128g
like
146
Text Generation
Transformers
PyTorch
English
llama
text-generation-inference
License:
other
Model card
Files
Files and versions
Community
9
Train
Deploy
Use this model
refs/pr/9
pygmalion-13b-4bit-128g
/
quantize_config.json
Pernekhan
Create quantize_config.json
5f7a136
verified
10 months ago
raw
Copy download link
history
blame
Safe
84 Bytes
{
"bits"
:
4
,
"desc_act"
:
false
,
"group_size"
:
128
,
"true_sequential"
:
true
}