x-square-robot/X2-Turn-4B-0812
Full fine-tune vs mistralai/Voxtral-Mini-4B-Realtime-2602. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 4/4, Norms 54/65, MLP 128/128, Attention 224/224, other 2/2
Full fine-tune vs mistralai/Voxtral-Mini-4B-Realtime-2602. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 4/4, Norms 54/65, MLP 128/128, Attention 224/224, other 2/2