prithivMLmods/SmolLM2-CoT-360M
Full fine-tune vs HuggingFaceTB/SmolLM2-360M-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128
4 derivatives checked
- reaperdoesntknow/SMOLM2Prover: Full fine-tune
- reaperdoesntknow/SMOLM2Prover-GGUF: Full fine-tune
- DevQuasar-6/prithivMLmods.SmolLM2-CoT-360M-GGUF: Same weights, converted
- prithivMLmods/SmolLM2-CoT-360M-GGUF: Partial fine-tune
2 other repos hold byte-for-byte identical weight files.