Mapika/decider-2b
Partial fine-tune (fewer layers) vs Qwen/Qwen3.5-2B-Base. Mapika/decider-2b matches part of Qwen/Qwen3.5-2B-Base (320 of its 632 tensors; the rest of Qwen/Qwen3.5-2B-Base has no counterpart). On the shared part: Partial change: 73% of the weights changed (attention, mlp, norms), in 24 of 24 layers.
Tensors changed: Attention 132/168, Norms 41/79, Embeddings 0/1, MLP 72/72
5 derivatives checked
- Mapika/decider-2b-GGUF: Same weights, converted
- cosetoenor/decider-2b-GGUF: LoRA-style
- DreamBlooms/decider-2b-GGUF: Full fine-tune
- midium-ai/decider-2b-dwq-4bit: Quantization
- nativ-community/decider-2b: Same weights, repacked