lemon07r/Gemma-2-Ataraxy-v4b-9B
Full fine-tune vs lemon07r/Gemma-2-Ataraxy-v3b-9B. Fine-tune: 98% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 1/1, Norms 169/169, MLP 123/126, Attention 164/168
2 derivatives checked
- mradermacher/Gemma-2-Ataraxy-v4b-9B-i1-GGUF: Quantization
- mradermacher/Gemma-2-Ataraxy-v4b-9B-GGUF: Same weights, converted
20 other repos hold byte-for-byte identical weight files.