8F-ai/Verus-R1
Partial fine-tune vs Qwen/Qwen3.5-2B. Partial change: 86% of the weights changed (attention, embeddings, mlp, norms), in 24 of 24 layers.
Tensors changed: Attention 142/264, Norms 81/177, Embeddings 2/4, MLP 76/172
2 derivatives checked
- mradermacher/Verus-R1-GGUF: Same weights, converted
- mradermacher/Verus-R1-i1-GGUF: Quantization