anakin87/gemma-2-2b-neogenesis-ita
Partial fine-tune vs google/gemma-2-2b-it. Partial change: 40% of the weights changed (attention, embeddings, mlp, norms), in 19 of 26 layers.
Tensors changed: Embeddings 1/1, Norms 18/105, MLP 18/78, Attention 24/104
4 derivatives checked
- mradermacher/gemma-2-2b-neogenesis-ita-i1-GGUF: Quantization
- featherless-ai-quants/anakin87-gemma-2-2b-neogenesis-ita-GGUF: Quantization
- mradermacher/gemma-2-2b-neogenesis-ita-GGUF: Same weights, converted
- tensorblock/gemma-2-2b-neogenesis-ita-GGUF: Quantization