Satori-reasoning/Satori-SWE-RL-32B
Full fine-tune vs Satori-reasoning/Satori-SWE-SFT-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 125/129, MLP 192/192, Attention 448/448, lm_head 1/1
2 derivatives checked
- mradermacher/Satori-SWE-RL-32B-i1-GGUF: Quantization
- mradermacher/Satori-SWE-RL-32B-GGUF: Quantization