Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
TheBloke
/
Nous-Capybara-3B-v1.9-GPTQ
like
8
Text Generation
Transformers
Safetensors
LDJnr/LessWrong-Amplify-Instruct
LDJnr/Pure-Dove
LDJnr/Verified-Camel
English
stablelm_epoch
sft
StableLM
custom_code
4-bit precision
gptq
License:
mit
Model card
Files
Files and versions
xet
Community
2
Deploy
Use this model
gptq-8bit-32g-actorder_True
Nous-Capybara-3B-v1.9-GPTQ
/
quantize_config.json
TheBloke
GPTQ model commit
fd69a19
about 2 years ago
raw
Copy download link
history
blame
133 Bytes
{
"bits"
:
8
,
"group_size"
:
32
,
"damp_percent"
:
0.01
,
"desc_act"
:
true
,
"sym"
:
true
,
"true_sequential"
:
true
}