Youlln/4PRYMMAL-GEMMA2-9B-SLERP
Full fine-tune vs ehristoforu/Gemma2-9b-it-train6. 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
1 derivatives checked
- mradermacher/4PRYMMAL-GEMMA2-9B-SLERP-GGUF: Same weights, converted