Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
WizardLM-7B-uncensored-GPTQ
like
184
Text Generation
Transformers
Safetensors
ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
llama
uncensored
text-generation-inference
4-bit precision
License:
other
Model card
Files
Files and versions
Community
13
Train
Deploy
Use this model
latest
WizardLM-7B-uncensored-GPTQ
/
quantize_config.json
TheBloke
Update for Transformers GPTQ support
57245b0
9 months ago
raw
history
blame
91 Bytes
{
"bits"
:
4
,
"desc_act"
:
true
,
"group_size"
:
128
,
"model_file_base_name"
:
"model"
}