cl-nagoya/ruri-v3-310m
Full fine-tune vs cl-nagoya/ruri-v3-pt-310m. Fine-tune: 100% of the weights changed, across 25 of 25 layers.
Tensors changed: Embeddings 2/2, Norms 50/50, Attention 50/50, MLP 50/50
5 derivatives checked
- sionic-ai/comsat-embed-ja-0.3b-preview: LoRA-style
- Targoyle/ruri-v3-310m-GGUF: Quantization
- genshiai-daichi/med-ruri-v3-310m-v2-from-ruri: Full fine-tune
- masahiroid/ruri-v3-310m-mlx: Same weights, converted
- genshiai-daichi/med-ruri-v3-310m: Full fine-tune
3 other repos hold byte-for-byte identical weight files.