Pentium95/SmolLMathematician-3B
LoRA-style vs HuggingFaceTB/SmolLM3-3B-Base. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 72/144
1 derivatives checked
- mradermacher/SmolLMathematician-3B-GGUF: Same weights, converted