AXCXEPT/EZO-gemma-2-2b-jpn-it
Full fine-tune vs google/gemma-2-2b-jpn-it. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: Embeddings 1/1, Norms 79/105, MLP 78/78, Attention 104/104
3 derivatives checked
- MCZK/EZO-gemma-2-2b-jpn-it-GGUF: Same weights, converted
- mradermacher/EZO-gemma-2-2b-jpn-it-i1-GGUF: Quantization
- mradermacher/EZO-gemma-2-2b-jpn-it-GGUF: Same weights, converted