robertgshaw2
/

tinyllama-sq-test

Text Generation

text-generation-inference

Inference Endpoints

8-bit precision

Model card Files Files and versions Community

tinyllama-sq-test / quant_config.json

robertgshaw2's picture

Upload folder using huggingface_hub

88cfe09 verified 8 months ago

history blame contribute delete

93 Bytes

	{
	"qkv": "per-token",
	"out": "per-tensor",
	"fc1": "per-token",
	"fc2": "per-tensor"
	}