BricksDisplay
/

Mistral-7B-v0.1-q4

Text Generation

Inference Endpoints

Model card Files Files and versions Community

Mistral-7B-v0.1-q4 / quantize_config.json

hans00's picture

Upload folder using huggingface_hub

a38d66e verified 8 months ago

history blame contribute delete

111 Bytes

	{
	"per_channel": false,
	"reduce_range": false,
	"quantize_mode": "hqq",
	"per_model_config": {}
	}