Adding the Open Portuguese LLM Leaderboard Evaluation Results (#1)

- Adding the Open Portuguese LLM Leaderboard Evaluation Results (aa8a51e254387ed99b1e04f20d72d5da7e8d9900)


Co-authored-by: Open PT LLM Leaderboard PR Bot <leaderboard-pt-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,18 +1,139 @@
 ---
 language:
-  - pt
-  - en
+- pt
+- en
 license: cc
 tags:
-  - text-generation-inference
-  - transformers
-  - qwen
-  - gguf
-  - brazil
-  - brasil
-  - portuguese
+- text-generation-inference
+- transformers
+- qwen
+- gguf
+- brazil
+- brasil
+- portuguese
 base_model: Qwen/Qwen1.5-7B-Chat
 pipeline_tag: text-generation
+model-index:
+- name: CabraQwen7b
+  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: 69.21
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen7b
+      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: 56.05
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen7b
+      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: 43.23
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen7b
+      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: 88.52
+      name: f1-macro
+    - type: pearson
+      value: 76.17
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen7b
+      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: 57.8
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen7b
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HateBR Binary
+      type: eduagarcia/portuguese_benchmark
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: f1_macro
+      value: 76.32
+      name: f1-macro
+    - type: f1_macro
+      value: 69.69
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen7b
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: tweetSentBR
+      type: eduagarcia-temp/tweetsentbr
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: f1_macro
+      value: 65.96
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen7b
+      name: Open Portuguese LLM Leaderboard
 ---
 # Cabra Qwen 7b
 <img src="https://uploads-ssl.webflow.com/65f77c0240ae1c68f8192771/660b1a4df7de79066317cafe_cabra2.png" width="400" height="400">
@@ -166,3 +287,20 @@ O modelo é destinado, por agora, a fins de pesquisa. As áreas e tarefas de pes
 |                             |         | exam_id__2015-16     | 3      | acc      | 0.4125 | ± 0.0318 |
 | portuguese_hate_speech_binary | 1.0   | all                  | 25     | f1_macro | 0.6969 | ± 0.0119 |
 |                             |         | all                  | 25     | acc      | 0.7356 | ± 0.0107 |
+
+# [Open Portuguese LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/nicolasdec/CabraQwen7b)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**66.99**|
+|ENEM Challenge (No Images)|    69.21|
+|BLUEX (No Images)         |    56.05|
+|OAB Exams                 |    43.23|
+|Assin2 RTE                |    88.52|
+|Assin2 STS                |    76.17|
+|FaQuAD NLI                |    57.80|
+|HateBR Binary             |    76.32|
+|PT Hate Speech Binary     |    69.69|
+|tweetSentBR               |    65.96|
+