HuggingFaceTB/finemath-ablation-infiwebmath
Full fine-tune vs meta-llama/Llama-3.2-3B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 112/112
4 derivatives checked
- mradermacher/finemath-ablation-infiwebmath-i1-GGUF: Quantization
- mradermacher/finemath-ablation-infiwebmath-GGUF: Same weights, converted
- DevQuasar-6/HuggingFaceTB.finemath-ablation-infiwebmath-GGUF: Quantization
- bunnycore/Smol-Llama-3.2-3B: Full fine-tune