Adding Evaluation Results (#1)

- Adding Evaluation Results (34585064e04aeabf98b2ff7a3fd7859b210be304)


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

README.md

@@ -1,17 +1,120 @@
 ---
 language:
-  - en
+- en
 license: other
 tags:
-  - art
-  - philosophy
-  - romance
-  - jokes
-  - advice
-  - code
-  - companionship
+- art
+- philosophy
+- romance
+- jokes
+- advice
+- code
+- companionship
 license_name: llama3
 license_link: LICENSE
+model-index:
+- name: Scarlett-Llama-3-8B-v1.0
+  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: 62.12
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Scarlett-Llama-3-8B-v1.0
+      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: 83.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Scarlett-Llama-3-8B-v1.0
+      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: 66.36
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Scarlett-Llama-3-8B-v1.0
+      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: 55.98
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Scarlett-Llama-3-8B-v1.0
+      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: 77.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Scarlett-Llama-3-8B-v1.0
+      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: 43.21
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Scarlett-Llama-3-8B-v1.0
+      name: Open LLM Leaderboard
 ---
 
 **Scarlett-Llama-3-8B-v1.0**
@@ -82,3 +185,17 @@ Example 4
 
 
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64aea8ff67511bd3d965697b/95YaYsebBPJqQ-oo8841f.jpeg)
+
+# [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_ajibawa-2023__Scarlett-Llama-3-8B-v1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |64.92|
+|AI2 Reasoning Challenge (25-Shot)|62.12|
+|HellaSwag (10-Shot)              |83.98|
+|MMLU (5-Shot)                    |66.36|
+|TruthfulQA (0-shot)              |55.98|
+|Winogrande (5-shot)              |77.90|
+|GSM8k (5-shot)                   |43.21|
+