casperhansen
/

mpt-7b-8k-chat-awq

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

mpt-7b-8k-chat-awq / generation_config.json

casperhansen's picture

MPT 7B 8K quantized

5c660fe over 1 year ago

121 Bytes

	{
	"_from_model_config": true,
	"transformers_version": "4.30.2",
	"use_cache": false,
	"eos_token_id": [0, 50278]
	}