PKU-DS-LAB/FairyR1-32B
Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-32B. Fine-tune: 98% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 0/1, Attention 448/448, MLP 192/192, Norms 127/129, lm_head 1/1
4 derivatives checked
- bartowski/PKU-DS-LAB_FairyR1-32B-GGUF: Same weights, converted
- mradermacher/FairyR1-32B-i1-GGUF: Quantization
- DevQuasar/PKU-DS-LAB.FairyR1-32B-GGUF: Same weights, converted
- mradermacher/FairyR1-32B-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.