rinna/gemma-2-baku-2b
Full fine-tune vs google/gemma-2-2b. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: Embeddings 1/1, Norms 105/105, MLP 78/78, Attention 104/104
6 derivatives checked
- mradermacher/gemma-2-baku-2b-i1-GGUF: Quantization
- lmg-anon/vntl-gemma2-2b-gguf: Full fine-tune
- DevQuasar-10/rinna.gemma-2-baku-2b-GGUF: Same weights, converted
- mradermacher/gemma-2-baku-2b-GGUF: Same weights, converted
- tensorblock/gemma-2-baku-2b-GGUF: Quantization
- Sakalti/Gemma-2-Baku-Finetune: Same weights, converted