bunnycore/Qwen3-1.7B-Nyx-abliterated
Partial fine-tune vs bunnycore/Qwen3-1.7B-Nyx-V3. Partial change: 45% of the weights changed (attention, embeddings, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 89/113, MLP 28/84, Attention 28/112
2 derivatives checked
- mradermacher/Qwen3-1.7B-Nyx-abliterated-i1-GGUF: Quantization
- mradermacher/Qwen3-1.7B-Nyx-abliterated-GGUF: Same weights, converted