google/t5gemma-l-l-ul2-it
Partial fine-tune vs google/t5gemma-l-l-ul2. Partial change: 79% of the weights changed (attention, embeddings, mlp, norms), in 24 of 24 layers.
Tensors changed: Embeddings 1/2, Attention 288/288, MLP 144/144, Norms 242/242
Partial fine-tune vs google/t5gemma-l-l-ul2. Partial change: 79% of the weights changed (attention, embeddings, mlp, norms), in 24 of 24 layers.
Tensors changed: Embeddings 1/2, Attention 288/288, MLP 144/144, Norms 242/242