mradermacher/SmolLM3-3B-GSM8K-SFT-GGUF
Same weights, converted vs HuggingFaceTB/SmolLM3-3B-GSM8K-SFT. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/144
Same weights, converted vs HuggingFaceTB/SmolLM3-3B-GSM8K-SFT. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/144