rodrigomt/gama-4b

Full fine-tune vs CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it. Fine-tune: 90% of the weights changed, across 34 of 34 layers.

Tensors changed: Embeddings 1/4, Norms 191/316, MLP 102/210, Attention 136/352, other 1/1

1 derivatives checked

• mradermacher/gama-4b-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse