Goedel-LM/Goedel-Prover-V2-32B
Full fine-tune vs Qwen/Qwen3-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 257/257, MLP 192/192, Attention 256/256, lm_head 1/1
3 derivatives checked
- mradermacher/Goedel-Prover-V2-32B-i1-GGUF: Quantization
- DevQuasar/Goedel-LM.Goedel-Prover-V2-32B-GGUF: Same weights, converted
- mradermacher/Goedel-Prover-V2-32B-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.