stan-hua
/

Phi-3-small-7B-Instruct-GPTQ-4bit

Text Generation

4-bit precision

Model card Files Files and versions Community

Phi-3-small-7B-Instruct-GPTQ-4bit / generation_config.json

stan-hua's picture

GPTQ model for microsoft/Phi-3-small-8k-instruct: {'bits': 4, 'dataset': 'c4', 'group_size': 128, 'desc_act': False}

5d6c698 verified 6 months ago

history blame contribute delete

143 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 100257,
	"eos_token_id": [
	100257,
	100266
	],
	"transformers_version": "4.41.2"
	}