RedHatAI/Voxtral-Mini-4B-Realtime-2602
Full fine-tune vs mistralai/Ministral-3-3B-Base-2512. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: Embeddings 1/1, Norms 53/53, MLP 78/78, Attention 104/104, other 1/1
Full fine-tune vs mistralai/Ministral-3-3B-Base-2512. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: Embeddings 1/1, Norms 53/53, MLP 78/78, Attention 104/104, other 1/1