nm-testing
/

Mixtral-8x7B-Instruct-v0.1-W4A16-channel-quantized

compressed-tensors

Model card Files Files and versions Community

Mixtral-8x7B-Instruct-v0.1-W4A16-channel-quantized / generation_config.json

sadkins65's picture

Upload folder using huggingface_hub

82046e5 verified 5 months ago

history blame contribute delete

111 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"transformers_version": "4.43.4"
	}