animaslabs/nemotron-speech-streaming-en-0.6b-mlx
Full fine-tune vs nvidia/nemotron-speech-streaming-en-0.6b. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: MLP 96/96, Norms 240/240
Full fine-tune vs nvidia/nemotron-speech-streaming-en-0.6b. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: MLP 96/96, Norms 240/240