omarabb315/gemma_muharaf_12b_model

Full fine-tune vs unsloth/gemma-3-12b-it. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Embeddings 4/4, Norms 146/400, MLP 244/252, Attention 405/408, other 1/1

1 derivatives checked

• mradermacher/gemma_muharaf_12b_model-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse