Adding Evaluation Results (#8)

- Adding Evaluation Results (cdea28de8eab555e22a96bc8fef329d6b2f2c8f4)


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

README.md

@@ -1,8 +1,111 @@
 ---
-license: apache-2.0
 language:
 - pt
 - en
+license: apache-2.0
+model-index:
+- name: open-cabrita3b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 33.79
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=22h/open-cabrita3b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 55.35
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=22h/open-cabrita3b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 25.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=22h/open-cabrita3b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 38.5
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=22h/open-cabrita3b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 59.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=22h/open-cabrita3b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 0.99
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=22h/open-cabrita3b
+      name: Open LLM Leaderboard
 ---
 The Cabrita model is a collection of continued pre-trained and tokenizer-adapted models for the Portuguese language.
 This artifact is the 3 billion size variant. 
@@ -19,4 +122,17 @@ open_llama_3b option.
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_22h__open-cabrita3b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |35.54|
+|AI2 Reasoning Challenge (25-Shot)|33.79|
+|HellaSwag (10-Shot)              |55.35|
+|MMLU (5-Shot)                    |25.16|
+|TruthfulQA (0-shot)              |38.50|
+|Winogrande (5-shot)              |59.43|
+|GSM8k (5-shot)                   | 0.99|
+