AI-MO/Kimina-Prover-Distill-8B
Full fine-tune vs Qwen/Qwen3-8B. Fine-tune: 92% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 0/1, Norms 143/145, MLP 108/108, Attention 144/144, lm_head 1/1
5 derivatives checked
- gabriellarson/Kimina-Prover-Distill-8B-GGUF: Quantization
- mradermacher/Kimina-Prover-Distill-8B-i1-GGUF: Quantization
- DevQuasar/AI-MO.Kimina-Prover-Distill-8B-GGUF: Same weights, converted
- mradermacher/Kimina-Prover-Distill-8B-GGUF: Same weights, converted
- tensorblock/AI-MO_Kimina-Prover-Distill-8B-GGUF: Quantization