Mapika/decider-0.8b
Partial fine-tune (fewer layers) vs Qwen/Qwen3.5-0.8B-Base. Mapika/decider-0.8b 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: Partial change: 66% of the weights changed (attention, mlp, norms), in 24 of 24 layers.
Tensors changed: Attention 132/168, Norms 23/79, Embeddings 0/1, MLP 72/72
4 derivatives checked
- mradermacher/decider-0.8b-GGUF: Same weights, converted
- DreamBlooms/decider-0.8b-GGUF: Quantization
- seongukjeong/decider-0.8b-GGUF: Quantization
- IqSantiagow/edceleste-decider-0.8b: LoRA-style