yamatazen/Gemma2-Ataraxy-Psycho-9B
Full fine-tune vs UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 1/1, Norms 169/169, MLP 126/126, Attention 168/168
3 derivatives checked
- mradermacher/Gemma2-Ataraxy-Psycho-9B-i1-GGUF: Quantization
- mradermacher/Gemma2-Ataraxy-Psycho-9B-GGUF: Same weights, converted
- yamatazen/Gemma2-ObsidianLight-9B: Full fine-tune