AI-MO/Kimina-Prover-72B
Full fine-tune vs Qwen/Qwen2.5-72B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, MLP 240/240, Attention 560/560, Norms 157/161, lm_head 1/1
3 derivatives checked
- mradermacher/Kimina-Prover-72B-i1-GGUF: Quantization
- gabriellarson/Kimina-Prover-72B-GGUF: Quantization
- DevQuasar/AI-MO.Kimina-Prover-72B-GGUF: Same weights, converted