aman-jaglan/arc-advisor
Full fine-tune vs Qwen/Qwen3-4B. Fine-tune: 90% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 0/1, Norms 84/145, MLP 108/108, Attention 144/144
2 derivatives checked
- mradermacher/arc-advisor-i1-GGUF: Quantization
- mradermacher/arc-advisor-GGUF: Same weights, converted