AI-MO/Kimina-Prover-RL-1.7B
Partial fine-tune vs AI-MO/Kimina-Prover-Distill-1.7B. Partial change: 69% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 92/113, MLP 84/84, Attention 112/112
2 derivatives checked
- mradermacher/Kimina-Prover-RL-1.7B-i1-GGUF: Quantization
- mradermacher/Kimina-Prover-RL-1.7B-GGUF: Same weights, converted