RamaBashar22/nemotron-3.5-asr-streaming-0.6b-jordanian

Full fine-tune vs nvidia/nemotron-3.5-asr-streaming-0.6b. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: other 102/102, Embeddings 1/1, Norms 288/288, MLP 96/96, Attention 168/168

On the Hub · Downloads on Model Pulse