jsbaicenter/Aztec-Coder-4B
Full fine-tune (fewer layers) vs Qwen/Qwen3.5-4B. jsbaicenter/Aztec-Coder-4B matches part of Qwen/Qwen3.5-4B (426 of its 738 tensors; the rest of Qwen/Qwen3.5-4B has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, MLP 96/96, Attention 176/224, Norms 45/105
3 derivatives checked
- mradermacher/Aztec-Coder-4B-i1-GGUF: Quantization
- prithivMLmods/Aztec-Coder-4B-GGUF: Same weights, converted
- mradermacher/Aztec-Coder-4B-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.