Update README.md

README.md

@@ -34,7 +34,7 @@ Our approach ensures that the model retains its original strengths while acquiri
 3. [Evaluation](#evaluation)
     - [GPT4ALL](#gpt4all)
     - [Language Model evaluation Harness](#language-model-evaluation-harness)
-    - [BigBench](#bbh)
+    - [BigBench](#big-bench)
     - [MMLU](#mmlu)
     - [TruthfulQA](#truthfulqa)
     - [MT-Bench (German)](#mt-bench-german)