seonglae
/

wizardlm-7b-uncensored-gptq

Text Generation

text-generation-inference

Model card Files Files and versions Community

wizardlm-7b-uncensored-gptq / generation_config.json

seonglae's picture

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

2c100e4 about 1 year ago

history blame contribute delete

No virus

132 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"pad_token_id": 0,
	"transformers_version": "4.30.2"
	}