SpatialAxiom/SpatialAxiom-35B-A3B
Full fine-tune (fewer layers) vs Qwen/Qwen3.5-35B-A3B. SpatialAxiom/SpatialAxiom-35B-A3B matches part of Qwen/Qwen3.5-35B-A3B (1026 of its 1811 tensors; the rest of Qwen/Qwen3.5-35B-A3B has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: MLP 392/392, lm_head 1/1, Embeddings 4/4, Attention 354/388, Norms 182/241
1 derivatives checked
- bartowski/SpatialAxiom_SpatialAxiom-35B-A3B-GGUF: Same weights, converted