qihoo360/Light-R1-7B-DS

Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-7B. Fine-tune: 93% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 0/1, Attention 196/196, MLP 84/84, Norms 55/57, lm_head 1/1

3 derivatives checked

• mradermacher/Light-R1-7B-DS-i1-GGUF: Quantization
• mradermacher/Light-R1-7B-DS-GGUF: Same weights, converted
• DevQuasar-11/qihoo360.Light-R1-7B-DS-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse