UT-IFML/dQwen3.5-9B-Base
Full fine-tune (fewer layers) vs Qwen/Qwen3.5-9B. UT-IFML/dQwen3.5-9B-Base matches part of Qwen/Qwen3.5-9B (427 of its 775 tensors; the rest of Qwen/Qwen3.5-9B has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, MLP 96/96, Attention 222/224, Norms 105/105