bunnycore/Qwen3-1.7B-Nyx-V3
Partial fine-tune vs POLARIS-Project/Polaris-1.7B-Preview. Partial change: 82% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 26/113, MLP 84/84, Attention 109/112
3 derivatives checked
- mradermacher/Qwen3-1.7B-Nyx-V3-i1-GGUF: Quantization
- mradermacher/Qwen3-1.7B-Nyx-V3-GGUF: Same weights, converted
- bunnycore/Qwen3-1.7B-Nyx-abliterated: Partial fine-tune