prithivMLmods/Nexus-9B-CodeCore-Merge
Full fine-tune vs Qwen/Qwen3.5-9B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/5, MLP 96/211, Attention 210/336, other 0/1, Norms 105/221
3 derivatives checked
- mradermacher/Nexus-9B-CodeCore-Merge-i1-GGUF: Quantization
- mradermacher/Nexus-9B-CodeCore-Merge-GGUF: Same weights, converted
- prithivMLmods/Nexus-9B-CodeCore-Merge-GGUF: Same weights, converted