Mapika/decider-4b
Partial fine-tune (fewer layers) vs Qwen/Qwen3.5-4B-Base. Mapika/decider-4b matches part of Qwen/Qwen3.5-4B-Base (426 of its 738 tensors; the rest of Qwen/Qwen3.5-4B-Base has no counterpart). On the shared part: Partial change: 85% of the weights changed (attention, mlp, norms), in 32 of 32 layers.
Tensors changed: Embeddings 0/1, MLP 96/96, Attention 177/224, Norms 47/105
5 derivatives checked
- Mapika/decider-4b-GGUF: Same weights, converted
- mradermacher/decider-4b-GGUF: LoRA-style
- mindchain/decider-4b-v2-GGUF: Quantization
- midium-ai/decider-4b-dwq-4bit: Quantization
- hayriyigit/decider-4b-tr: LoRA-style
1 other repos hold byte-for-byte identical weight files.