Adding the Open Portuguese LLM Leaderboard Evaluation Results

README.md

@@ -9,6 +9,153 @@ datasets:
 - argilla/ultrafeedback-binarized-preferences-cleaned
 - jondurbin/truthy-dpo-v0.1
 pipeline_tag: text-generation
+model-index:
+- name: Faro-Yi-34B-DPO
+  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: 73.55
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wenbopan/Faro-Yi-34B-DPO
+      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: 65.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wenbopan/Faro-Yi-34B-DPO
+      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: 55.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wenbopan/Faro-Yi-34B-DPO
+      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: 92.2
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wenbopan/Faro-Yi-34B-DPO
+      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: 79.78
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wenbopan/Faro-Yi-34B-DPO
+      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: 71.0
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wenbopan/Faro-Yi-34B-DPO
+      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: 85.12
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wenbopan/Faro-Yi-34B-DPO
+      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: 68.88
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wenbopan/Faro-Yi-34B-DPO
+      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: 72.24
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=wenbopan/Faro-Yi-34B-DPO
+      name: Open Portuguese LLM Leaderboard
 ---
 
 # Faro-Yi-9B-DPO
@@ -56,4 +203,23 @@ generated_ids = model.generate(input_ids, max_new_tokens=512, temperature=0.5)
 response = tokenizer.decode(generated_ids[0], skip_special_tokens=True) # Aye, matey! The Pythagorean theorem is a nautical rule that helps us find the length of the third side of a triangle. ...
 ```
 
-</details>
+</details>
+
+
+# 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/wenbopan/Faro-Yi-34B-DPO) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**73.82**|
+|ENEM Challenge (No Images)|    73.55|
+|BLUEX (No Images)         |    65.79|
+|OAB Exams                 |    55.85|
+|Assin2 RTE                |    92.20|
+|Assin2 STS                |    79.78|
+|FaQuAD NLI                |       71|
+|HateBR Binary             |    85.12|
+|PT Hate Speech Binary     |    68.88|
+|tweetSentBR               |    72.24|
+