ahmedeltawel/Qwen3.5-0.8B-hsb-dsb
Full fine-tune (fewer layers) vs Qwen/Qwen3.5-0.8B-Base. ahmedeltawel/Qwen3.5-0.8B-hsb-dsb matches part of Qwen/Qwen3.5-0.8B-Base (320 of its 488 tensors; the rest of Qwen/Qwen3.5-0.8B-Base has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Attention 136/168, Norms 43/79, Embeddings 1/1, MLP 72/72