inference-net/Schematron-3B
Full fine-tune vs meta-llama/Llama-3.2-3B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 15/57, MLP 84/84, Attention 112/112
5 derivatives checked
- mradermacher/Schematron-3B-i1-GGUF: Quantization
- mradermacher/Schematron-3B-GGUF: Same weights, converted
- DevQuasar/inference-net.Schematron-3B-GGUF: Same weights, converted
- MaziyarPanahi/Schematron-3B-GGUF: Same weights, converted
- Open4bits/Schematron-3B-gguf: Quantization
2 other repos hold byte-for-byte identical weight files.