princeton-nlp/gemma-2-9b-it-SimPO
Full fine-tune vs google/gemma-2-9b-it. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 1/1, Norms 108/169, MLP 126/126, Attention 168/168
5 derivatives checked
- mradermacher/gemma-2-9b-it-SimPO-i1-GGUF: Quantization
- QuantFactory/gemma-2-9b-it-SimPO-rudpo-GGUF: Quantization
- mradermacher/gemma-2-9b-it-SimPO-GGUF: Same weights, converted
- pipihand01/gemma-2-9b-it-SimPO-GGUF: Same weights, converted
- MawaredHR/Mawared_GS: LoRA-style
1 other repos hold byte-for-byte identical weight files.