grimjim
/

Mistral-Nemo-Instruct-2407-12B-6.4bpw-exl2

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Mistral-Nemo-Instruct-2407-12B-6.4bpw-exl2 / params.json

grimjim's picture

Initial release

ac7f299 5 months ago

204 Bytes

	{
	"dim": 5120,
	"n_layers": 40,
	"head_dim": 128,
	"hidden_dim": 14336,
	"n_heads": 32,
	"n_kv_heads": 8,
	"norm_eps": 1e-05,
	"vocab_size": 131072,
	"rope_theta": 1000000.0
	}