Update tools/benchmarks/llm_eval_harness/meta_eval_reproduce/README.md

Co-authored-by: Hamid Shojanazeri <[email protected]>

Author: wukaixingxp

tools/benchmarks/llm_eval_harness/meta_eval_reproduce/README.md

@@ -5,7 +5,6 @@ As Meta Llama models gain popularity, evaluating these models has become increas
 
 ## Disclaimer
 
-### Important Notes
 
 1. **This tutorial is not the official implementation** of Meta Llama evaluation. It is based on public third-party libraries, and the implementation may differ slightly from our internal evaluation, leading to minor differences in the reproduced numbers.
 2. **Model Compatibility**: This tutorial is specifically for Llama 3 based models, as our prompts include Meta Llama 3 special tokens, e.g. `<|start_header_id|>user<|end_header_id|>`. It will not work with models that are not based on Llama 3.