jburtoft
/

Trinity-Nano-Neuron-TP1

neuronx-distributed-inference

Mixture of Experts

Model card Files Files and versions

Trinity-Nano-Neuron-TP1 / weights

Commit History

Mar 5

01:51
Trinity-Nano compiled for Neuron TP=1 BS=1 seq_len=2048 (SDK 2.28, pre-sharded weights)

jburtoft

Verified signature
0312d1a