melsiddieg/gemma2-2b-full-arud-aren-1.5k

Partial fine-tune vs unsloth/gemma-2b-it. Partial change: 79% of the weights changed (attention, mlp, norms), in 18 of 18 layers.

Tensors changed: Embeddings 0/1, Norms 18/37, MLP 54/54, Attention 72/72

2 derivatives checked

On the Hub · Downloads on Model Pulse