dphn/dolphin-2.9.1-llama-3-8b
Full fine-tune vs meta-llama/Meta-Llama-3-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
6 derivatives checked
- legraphista/dolphin-2.9.1-llama-3-8b-IMat-GGUF: Same weights, converted
- mradermacher/dolphin-2.9.1-llama-3-8b-i1-GGUF: Quantization
- mradermacher/dolphin-2.9.1-llama-3-8b-GGUF: Same weights, converted
- tensorblock/dolphin-2.9.1-llama-3-8b-GGUF: Quantization
- nothingiisreal/L3-8B-dolphin-2.9.1-WritingPrompts: LoRA-style
- emnakamura/llama-3-MagicDolphin-8B: Full fine-tune
1 other repos hold byte-for-byte identical weight files.