Adding the Open Portuguese LLM Leaderboard Evaluation Results

README.md

@@ -1,6 +1,8 @@
 ---
+language:
+- en
 license: mit
-library_name: "trl"
+library_name: trl
 tags:
 - DPO
 - WeniGPT
@@ -8,7 +10,6 @@ base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT
 model-index:
 - name: Weni/WeniGPT-2.8.1-Zephyr-7B-zephyr-prompt-binarized
   results: []
-language: ['en']
 ---
 
 # Weni/WeniGPT-2.8.1-Zephyr-7B-zephyr-prompt-binarized
@@ -79,3 +80,22 @@ The following hyperparameters were used during training:
 
 ### Hardware
 - Cloud provided: runpod.io
+
+
+# Open Portuguese LLM Leaderboard Evaluation Results  
+
+Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/Weni/WeniGPT-2.8.1-Zephyr-7B-zephyr-prompt-binarized) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**50.64**|
+|ENEM Challenge (No Images)|    37.44|
+|BLUEX (No Images)         |    36.58|
+|OAB Exams                 |    35.03|
+|Assin2 RTE                |    88.48|
+|Assin2 STS                |    33.02|
+|FaQuAD NLI                |    45.45|
+|HateBR Binary             |    68.62|
+|PT Hate Speech Binary     |    56.79|
+|tweetSentBR               |    54.32|
+