dphn/dolphin-2.9.4-gemma2-2b
Full fine-tune vs google/gemma-2-2b. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: Norms 104/105, MLP 78/78, Attention 104/104
8 derivatives checked
- bartowski/dolphin-2.9.4-gemma2-2b-GGUF: Same weights, converted
- mradermacher/dolphin-2.9.4-gemma2-2b-i1-GGUF: Quantization
- mradermacher/dolphin-2.9.4-gemma2-2b-GGUF: Same weights, converted
- SirAB/Dolphin-gemma2-2b-finetuned-gguf-v2: LoRA-style
- bunnycore/dolphin-2.9.4-gemma2-2b-Q4_K_M-GGUF: Quantization
- DevQuasar-5/cognitivecomputations.dolphin-2.9.4-gemma2-2b-GGUF: Quantization
- itlwas/dolphin-2.9.4-gemma2-2b-Q4_K_M-GGUF: Quantization
- SirAB/Dolphin-gemma2-2b-finetuned-gguf: Full fine-tune
1 other repos hold byte-for-byte identical weight files.