Pythagoras-LM/Pythagoras-Prover-32B

Full fine-tune vs Qwen/Qwen3-32B. Fine-tune: 95% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 0/1, Norms 67/257, MLP 192/192, Attention 256/256, lm_head 0/1

1 derivatives checked

• mradermacher/Pythagoras-Prover-32B-GGUF: Quantization

On the Hub · Downloads on Model Pulse