Adding Evaluation Results

README.md

@@ -1,18 +1,121 @@
 ---
+language:
+- pt
+license: llama2
+library_name: transformers
 tags:
 - text-generation
 - pytorch
 - LLM
 - Portuguese
 - Llama 2
-inference: false
-license: llama2
-language:
-- pt
-pipeline_tag: text-generation
-library_name: transformers
 datasets:
 - dominguesm/CC-MAIN-2023-23
+inference: false
+pipeline_tag: text-generation
+model-index:
+- name: canarim-7b
+  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: 51.96
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dominguesm/canarim-7b
+      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: 77.52
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dominguesm/canarim-7b
+      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: 40.92
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dominguesm/canarim-7b
+      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: 40.03
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dominguesm/canarim-7b
+      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: 71.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dominguesm/canarim-7b
+      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: 9.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dominguesm/canarim-7b
+      name: Open LLM Leaderboard
 ---
 
 
@@ -121,4 +224,17 @@ If you want to cite **Canarim-7B**, you could use this:
 
 ## License
 
-Canarim-7B is released under the [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://ai.meta.com/llama/license/).
+Canarim-7B is released under the [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://ai.meta.com/llama/license/).
+# [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_dominguesm__canarim-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |48.63|
+|AI2 Reasoning Challenge (25-Shot)|51.96|
+|HellaSwag (10-Shot)              |77.52|
+|MMLU (5-Shot)                    |40.92|
+|TruthfulQA (0-shot)              |40.03|
+|Winogrande (5-shot)              |71.43|
+|GSM8k (5-shot)                   | 9.93|
+