vihangd
/

smartsolmix-4x10.7b-v1

SmartSolMix-4x10.7b-v1

An experimental MOE of various 10.7b models made with mergekit

TBD

Should work with chatml as well as alpaca style prompt templates

Safetensors

Model size

36.1B params

Tensor type

FP16

Model is too large to load in Inference API (serverless). To try the model, launch it on Inference Endpoints (dedicated) instead.