chaoliangUNSW/Jev-Style-0.8B-Decision-v3
Partial fine-tune (fewer layers) vs Qwen/Qwen3.5-0.8B. chaoliangUNSW/Jev-Style-0.8B-Decision-v3 matches part of Qwen/Qwen3.5-0.8B (320 of its 488 tensors; the rest of Qwen/Qwen3.5-0.8B 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 143/168, Norms 74/79, Embeddings 0/1, MLP 72/72
1 derivatives checked
- chaoliangUNSW/Jev-Style-0.8B-Decision-v3-GGUF: Same weights, converted