Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
j5ng
/
kullm-5.8b-GPTQ-8bit
like
2
Text Generation
Transformers
Korean
gpt_neox
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
66902db
kullm-5.8b-GPTQ-8bit
/
quantize_config.json
j5ng
init
25b2ef3
about 1 year ago
raw
Copy download link
history
blame
Safe
210 Bytes
{
"bits"
:
8
,
"group_size"
:
128
,
"damp_percent"
:
0.01
,
"desc_act"
:
true
,
"static_groups"
:
false
,
"sym"
:
true
,
"true_sequential"
:
true
,
"model_name_or_path"
:
null
,
"model_file_base_name"
:
null
}