jburtoft
/

Trinity-Nano-Neuron-TP1

neuronx-distributed-inference

Mixture of Experts

Model card Files Files and versions

Trinity-Nano-Neuron-TP1 / weights

12.2 GB

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

jburtoft's picture

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

0312d1a verified 4 months ago

tp0_sharded_checkpoint.safetensors

12.2 GB
xet

Trinity-Nano compiled for Neuron TP=1 BS=1 seq_len=2048 (SDK 2.28, pre-sharded weights) 4 months ago