Adding the Open Portuguese LLM Leaderboard Evaluation Results

README.md

@@ -1,8 +1,155 @@
 ---
 license: other
+base_model: moreh/MoMo-72B-lora-1.8.7-DPO
 license_name: tongyi-qianwen-license-agreement
 license_link: https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT
-base_model: moreh/MoMo-72B-lora-1.8.7-DPO
+model-index:
+- name: Smaug-72B-v0.1
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: ENEM Challenge (No Images)
+      type: eduagarcia/enem_challenge
+      split: train
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc
+      value: 77.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=abacusai/Smaug-72B-v0.1
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BLUEX (No Images)
+      type: eduagarcia-temp/BLUEX_without_images
+      split: train
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc
+      value: 68.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=abacusai/Smaug-72B-v0.1
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: OAB Exams
+      type: eduagarcia/oab_exams
+      split: train
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc
+      value: 58.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=abacusai/Smaug-72B-v0.1
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Assin2 RTE
+      type: assin2
+      split: test
+      args:
+        num_few_shot: 15
+    metrics:
+    - type: f1_macro
+      value: 92.96
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=abacusai/Smaug-72B-v0.1
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Assin2 STS
+      type: eduagarcia/portuguese_benchmark
+      split: test
+      args:
+        num_few_shot: 15
+    metrics:
+    - type: pearson
+      value: 81.79
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=abacusai/Smaug-72B-v0.1
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: FaQuAD NLI
+      type: ruanchaves/faquad-nli
+      split: test
+      args:
+        num_few_shot: 15
+    metrics:
+    - type: f1_macro
+      value: 77.47
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=abacusai/Smaug-72B-v0.1
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HateBR Binary
+      type: ruanchaves/hatebr
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: f1_macro
+      value: 85.65
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=abacusai/Smaug-72B-v0.1
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: PT Hate Speech Binary
+      type: hate_speech_portuguese
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: f1_macro
+      value: 65.31
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=abacusai/Smaug-72B-v0.1
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: tweetSentBR
+      type: eduagarcia/tweetsentbr_fewshot
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: f1_macro
+      value: 72.38
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=abacusai/Smaug-72B-v0.1
+      name: Open Portuguese LLM Leaderboard
 ---
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/pf4d6FA7DriRtVq5HCkxd.png)
@@ -194,4 +341,23 @@ Please cite the paper if you use data, model, or method in this repo.
   journal={arXiv preprint arXiv:2402.13228},
   year={2024}
 }
-```
+```
+
+
+# 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/abacusai/Smaug-72B-v0.1) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
+
+|          Metric          | Value  |
+|--------------------------|--------|
+|Average                   |**75.6**|
+|ENEM Challenge (No Images)|   77.82|
+|BLUEX (No Images)         |   68.29|
+|OAB Exams                 |   58.77|
+|Assin2 RTE                |   92.96|
+|Assin2 STS                |   81.79|
+|FaQuAD NLI                |   77.47|
+|HateBR Binary             |   85.65|
+|PT Hate Speech Binary     |   65.31|
+|tweetSentBR               |   72.38|
+