dphn/dolphin-2.9.1-yi-1.5-34b
Full fine-tune vs 01-ai/Yi-1.5-34B. Fine-tune: 100% of the weights changed, across 60 of 60 layers.
Tensors changed: Embeddings 1/1, Norms 83/121, MLP 180/180, Attention 240/240, lm_head 1/1
3 derivatives checked
- mradermacher/dolphin-2.9.1-yi-1.5-34b-i1-GGUF: Quantization
- mradermacher/dolphin-2.9.1-yi-1.5-34b-GGUF: Quantization
- mergekit-community/mergekit-passthrough-zpfenfn: Partial fine-tune (fewer layers)