radi-cho
/

Meta-Llama-3-70B-FLUTE

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Meta-Llama-3-70B-FLUTE / flute_config.json

Radostin Cholakov

Add nfl_w4g64.

979cce6 4 months ago

63 Bytes

	{
	"num_sms": 108,
	"num_bits": 4,
	"group_size": 64
	}