Update README.md

README.md

@@ -134,6 +134,22 @@ I used this string to visualize it, where 0 are original layers and 1 duplicated
 The main idea is that the input/output difference of middle layers is quite small, so replicating a middle layer has a small impact on the output. 
 The additional layers are designed to increase the model's capacity without breaking the information flow, which often creates "insane" self-merges.
 
+## 🏆 Evaluation
+
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_mlabonne__BigQwen2.5-Echo-47B-Instruct).
+
+TBD: add mlabonne/BigQwen2.5-52B-Instruct's results.
+
+|      Metric       |**BigQwen2.5-Echo-47B-Instruct**|Qwen2.5-32B-Instruct|
+|-------------------|----:|----:|
+|Avg.               |30.31|36.17|
+|IFEval (0-Shot)    |73.57|83.46|
+|BBH (3-Shot)       |44.52|56.49|
+|MATH Lvl 5 (4-Shot)| 3.47|0|
+|GPQA (0-shot)      | 8.61|11.74|
+|MuSR (0-shot)      |10.19|13.5|
+|MMLU-PRO (5-shot)  |41.49|51.85|
+
 ## 🧩 Configuration
 
 The following YAML configuration was used to produce this model:
@@ -315,17 +331,4 @@ pipeline = transformers.pipeline(
 
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
-```
-# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
-Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_mlabonne__BigQwen2.5-Echo-47B-Instruct)
-
-|      Metric       |Value|
-|-------------------|----:|
-|Avg.               |30.31|
-|IFEval (0-Shot)    |73.57|
-|BBH (3-Shot)       |44.52|
-|MATH Lvl 5 (4-Shot)| 3.47|
-|GPQA (0-shot)      | 8.61|
-|MuSR (0-shot)      |10.19|
-|MMLU-PRO (5-shot)  |41.49|
-
+```