Hugging Face's logo

seonglae
/
wizardlm-7b-uncensored-gptq

Text Generation
Transformers
llama
wizardlm
uncensored
gptq
quantization
auto-gptq
7b
4bit
Model card Files Community
wizardlm-7b-uncensored-gptq / quantize_config.json

Commit History

build: AutoGPTQ for ehartford/WizardLM-7B-Uncensored: 4bits, gr128, desc_act=False
3a44e62

seonglae commited on