Slim205/Lean-conjecturer

Full fine-tune vs deepseek-ai/DeepSeek-Prover-V1.5-SFT. Fine-tune: 100% of the weights changed, across 30 of 30 layers.

Tensors changed: Norms 61/61, Attention 120/120, MLP 90/90

1 derivatives checked

• mradermacher/Lean-conjecturer-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse