cmarkea
/

Mixtral-8x7B-Instruct-v0.1-4bit

Text Generation

Mixture of Experts

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Mixtral-8x7B-Instruct-v0.1-4bit / generation_config.json

Cyrile's picture

Upload 3 files

63dd2e8 verified 4 months ago

raw history blame contribute delete

No virus

111 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"transformers_version": "4.37.2"
	}