stan-hua
/

Gemma-7B-Instruct-AWQ-4bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Gemma-7B-Instruct-AWQ-4bit / generation_config.json

stan-hua's picture

AWQ model for google/gemma-7b-it: {'w_bit': 4, 'zero_point': True, 'q_group_size': 128, 'version': 'GEMM'}

057e8c2 verified 5 months ago

history blame contribute delete

153 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 2,
	"do_sample": true,
	"eos_token_id": 1,
	"pad_token_id": 0,
	"transformers_version": "4.41.1"
	}