MihaiPopa-1/SmolLM2-135M-Math
Full fine-tune vs HuggingFaceTB/SmolLM2-135M-Instruct. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 1/1, Norms 32/61, MLP 90/90, Attention 120/120
2 derivatives checked
- mradermacher/SmolLM2-135M-Math-i1-GGUF: Quantization
- mradermacher/SmolLM2-135M-Math-GGUF: Same weights, converted