mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0
Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Attention 196/196, MLP 84/84, Norms 34/57
2 derivatives checked
- bartowski/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF: Same weights, converted
- DevQuasar-7/mobiuslabsgmbh.DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF: Same weights, converted