qihoo360/TinyR1-32B-Preview
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
8 derivatives checked
- bartowski/qihoo360_TinyR1-32B-Preview-v0.2-GGUF: Quantization
- mradermacher/TinyR1-32B-Preview-i1-GGUF: Quantization
- bartowski/qihoo360_TinyR1-32B-Preview-v0.1-GGUF: Quantization
- bartowski/qihoo360_TinyR1-32B-Preview-GGUF: Quantization
- mradermacher/TinyR1-32B-Preview-GGUF: Quantization
- mmnga/TinyR1-32B-Preview-gguf: Quantization
- DevQuasar-9/qihoo360.TinyR1-32B-Preview-GGUF: Same weights, converted
- tensorblock/TinyR1-32B-Preview-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.