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

- Adding the Open Portuguese LLM Leaderboard Evaluation Results (27d1e2a3a6f667c0c15962d9e2910d125485f0c2)


Co-authored-by: Open PT LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,19 +1,140 @@
 ---
 language:
-  - pt
-  - en
+- pt
+- en
 license: cc
 tags:
-  - text-generation-inference
-  - transformers
-  - qwen
-  - gguf
-  - brazil
-  - brasil
-  - 14b
-  - portuguese
+- text-generation-inference
+- transformers
+- qwen
+- gguf
+- brazil
+- brasil
+- 14b
+- portuguese
 base_model: Qwen/Qwen1.5-14B-Chat
 pipeline_tag: text-generation
+model-index:
+- name: CabraQwen14b
+  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: 75.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen14b
+      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: 60.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen14b
+      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: 49.89
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen14b
+      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: 91.42
+      name: f1-macro
+    - type: pearson
+      value: 80.85
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen14b
+      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: 46.05
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen14b
+      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: 79.32
+      name: f1-macro
+    - type: f1_macro
+      value: 71.8
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen14b
+      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: 62.65
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen14b
+      name: Open Portuguese LLM Leaderboard
 ---
 # Cabra Qwen 14b
 <img src="https://uploads-ssl.webflow.com/65f77c0240ae1c68f8192771/660b1a4de37e3389b7220262_cabra3.png" width="400" height="400">
@@ -161,3 +282,20 @@ O modelo é destinado, por agora, a fins de pesquisa. As áreas e tarefas de pes
 |                             |         | exam_id__2014-15     | 3      | acc      | 0.5897 | ± 0.0323 |
 | portuguese_hate_speech_binary | 1.0   | all                  | 25     | f1_macro | 0.7180 | ± 0.0115 |
 |                             |         | all                  | 25     | acc      | 0.7462 | ± 0.0106 |
+
+# [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/CabraQwen14b)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**68.66**|
+|ENEM Challenge (No Images)|    75.16|
+|BLUEX (No Images)         |    60.78|
+|OAB Exams                 |    49.89|
+|Assin2 RTE                |    91.42|
+|Assin2 STS                |    80.85|
+|FaQuAD NLI                |    46.05|
+|HateBR Binary             |    79.32|
+|PT Hate Speech Binary     |    71.80|
+|tweetSentBR               |    62.65|
+