Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
Wizard-Vicuna-30B-Superhot-8K-GPTQ
like
20
Text Generation
Transformers
Safetensors
ehartford/wizard_vicuna_70k_unfiltered
English
llama
uncensored
custom_code
text-generation-inference
4-bit precision
gptq
License:
other
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
7ca06d4
Wizard-Vicuna-30B-Superhot-8K-GPTQ
/
generation_config.json
TheBloke
Initial merged FP16 model commit
a841cd9
over 1 year ago
raw
Copy download link
history
blame
Safe
137 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
1
,
"eos_token_id"
:
2
,
"pad_token_id"
:
0
,
"transformers_version"
:
"4.30.0.dev0"
}