realtreetune/rho-1b-sft-MATH
Full fine-tune vs microsoft/rho-math-1b-v0.1. Fine-tune: 100% of the weights changed, across 22 of 22 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 26/45, MLP 66/66, Attention 88/88
1 derivatives checked
- mradermacher/rho-1b-sft-MATH-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.