North-ML1/starlight-pro-1
Full fine-tune (fewer layers) vs Qwen/Qwen3.5-2B. North-ML1/starlight-pro-1 matches part of Qwen/Qwen3.5-2B (320 of its 632 tensors; the rest of Qwen/Qwen3.5-2B has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Attention 132/168, Norms 35/79, Embeddings 1/1, MLP 72/72
1 derivatives checked
- mradermacher/starlight-pro-1-GGUF: Same weights, converted