h-gajdov/full_moonshine_tiny_wup1_ep3_lr1e-4
Full fine-tune vs moonshine-ai/moonshine-tiny. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 1/1, Attention 72/72, Norms 34/34, MLP 48/48, other 5/5
Full fine-tune vs moonshine-ai/moonshine-tiny. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 1/1, Attention 72/72, Norms 34/34, MLP 48/48, other 5/5