Update README.md

README.md

@@ -23,7 +23,7 @@ From the original model creators:
 
 > DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance, we introduce DeepSeek-R1, which incorporates cold-start data before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen. DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
 
-> NOTE: Before running DeepSeek-R1 series models locally, we kindly recommend reviewing the [Usage Recommendation section](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B#usage-recommendations).
+> NOTE: Before running DeepSeek-R1 series models locally, we kindly recommend reviewing the [Usage Recommendation](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B#usage-recommendations) section.
 
 All quantized versions were generated using an appropriate imatrix created from datasets available at [eaddario/imatrix-calibration](https://huggingface.co/datasets/eaddario/imatrix-calibration).