bunnycore/Qwen3-1.7B-Nyx-Fusion
Partial fine-tune vs POLARIS-Project/Polaris-1.7B-Preview. Partial change: 51% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 14/113, MLP 51/84, Attention 70/112
2 derivatives checked
- mradermacher/Qwen3-1.7B-Nyx-Fusion-i1-GGUF: Quantization
- mradermacher/Qwen3-1.7B-Nyx-Fusion-GGUF: Same weights, converted