Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
stable-vicuna-13B-GPTQ
like
219
Text Generation
Transformers
Safetensors
OpenAssistant/oasst1
nomic-ai/gpt4all_prompt_generations
tatsu-lab/alpaca
English
llama
causal-lm
text-generation-inference
4-bit precision
gptq
arxiv:
2302.13971
License:
cc-by-nc-sa-4.0
Model card
Files
Files and versions
Community
29
Train
Deploy
Use this model
ecf7c95
stable-vicuna-13B-GPTQ
/
quantize_config.json
TheBloke
Create quantize_config.json
ecf7c95
over 1 year ago
raw
Copy download link
history
blame
Safe
81 Bytes
{
"bits"
:
4
,
"damp_percent"
:
0.01
,
"desc_act"
:
false
,
"group_size"
:
128
}