dphn/Dolphin3.0-Llama3.2-3B
Full fine-tune vs meta-llama/Llama-3.2-3B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 57/57, MLP 84/84, Attention 112/112
10 derivatives checked
- bartowski/Dolphin3.0-Llama3.2-3B-GGUF: Same weights, converted
- mlx-community/dolphin3.0-llama3.2-3B-4Bit: Quantization
- itlwas/Dolphin3.0-Llama3.2-3B-Q4_K_M-GGUF: Quantization
- mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF: Quantization
- mradermacher/Dolphin3.0-Llama3.2-3B-GGUF: Same weights, converted
- DevQuasar-7/cognitivecomputations.Dolphin3.0-Llama3.2-3B-GGUF: Same weights, converted
- DevQuasar/dphn.Dolphin3.0-Llama3.2-3B-GGUF: Same weights, converted
- Robert-Finance/Dolphin3.0-Llama3.2-3B-GGUF: Same weights, converted
- ysn-rfd/Dolphin3.0-Llama3.2-3B-GGUF: Quantization
- Bennmaru/Dolphin3.0-Llama3.2-3B-Q4_K_M-GGUF: Quantization