AI-MO/Kimina-Prover-Distill-0.6B
Full fine-tune vs Qwen/Qwen3-0.6B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 106/113, MLP 84/84, Attention 112/112
4 derivatives checked
- prithivMLmods/Kimina-Prover-AI-MO-GGUF: Same weights, converted
- mradermacher/Kimina-Prover-Distill-0.6B-i1-GGUF: Quantization
- mradermacher/Kimina-Prover-Distill-0.6B-GGUF: Same weights, converted
- AI-MO/Kimina-Prover-RL-0.6B: Partial fine-tune