dphn/dolphin-2.9.1-yi-1.5-9b
Full fine-tune vs 01-ai/Yi-1.5-9B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 23/97, MLP 144/144, Attention 192/192, lm_head 1/1
5 derivatives checked
- mradermacher/dolphin-2.9.1-yi-1.5-9b-GGUF: Same weights, converted
- mradermacher/dolphin-2.9.1-yi-1.5-9b-i1-GGUF: Quantization
- QuantFactory/dolphin-2.9.1-yi-1.5-9b-GGUF: Quantization
- baconnier/Gaston_dolphin-2.9.1-yi-1.5-9b: LoRA-style
- baconnier/Notaires_dolphin-2.9.1-yi-1.5-9b: LoRA-style
1 other repos hold byte-for-byte identical weight files.