olusegunola/DeepSeek-R1-Distill-Merge-Qwen-Math-1.5Bb
Full fine-tune vs Qwen/Qwen2.5-1.5B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196
2 derivatives checked
- mradermacher/DeepSeek-R1-Distill-Merge-Qwen-Math-1.5Bb-i1-GGUF: Quantization
- mradermacher/DeepSeek-R1-Distill-Merge-Qwen-Math-1.5Bb-GGUF: Same weights, converted