Adding Evaluation Results (#4)

- Adding Evaluation Results (f14cfcd237297d020b86e21322abb5562376a10c)


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

README.md

@@ -10,10 +10,148 @@ tags:
 datasets:
 - Locutusque/hercules-v2.0
 widget:
-  - example_title: "Derivative"
-    text: "<|im_start|>user\nIn this task, you are given a description of an object and its surroundings. Your task is to describe the motion of the object mentioned in the description using differential equations. The answer should be a mathematical expression in t. Description: A ball is thrown up at 30 ft/sec from 3 feet off the ground. Solve this step-by-step, explaining each step in detail.<|im_end|>\n<|im_start|>assistant\n"
-    output:
-      text: "Let h(t) be the height of the ball at time t after it was thrown. We know that when the ball is thrown, it has an initial velocity v0 = 30 ft/sec and initial height y0 = 3 ft. We also know that the acceleration due to gravity g = -32 ft/sec^2.\n\nTo solve for the motion of the ball, we can use the equation for vertical motion with acceleration due to gravity:\n\nh(t) = v0 * t + (1/2) * g * t^2 + y0\n\nSubstituting the values given in the problem, we get:\n\ny(t) = (30)(t) + (1/2)(-32)(t)^2 + 3\n\nNow, let's simplify the equation:\n\ny(t) = 30t - 16t^2 + 3\n\nThis is the final solution for the height of the ball as a function of time."
+- example_title: Derivative
+  text: '<|im_start|>user
+
+    In this task, you are given a description of an object and its surroundings. Your
+    task is to describe the motion of the object mentioned in the description using
+    differential equations. The answer should be a mathematical expression in t. Description:
+    A ball is thrown up at 30 ft/sec from 3 feet off the ground. Solve this step-by-step,
+    explaining each step in detail.<|im_end|>
+
+    <|im_start|>assistant
+
+    '
+  output:
+    text: 'Let h(t) be the height of the ball at time t after it was thrown. We know
+      that when the ball is thrown, it has an initial velocity v0 = 30 ft/sec and
+      initial height y0 = 3 ft. We also know that the acceleration due to gravity
+      g = -32 ft/sec^2.
+
+
+      To solve for the motion of the ball, we can use the equation for vertical motion
+      with acceleration due to gravity:
+
+
+      h(t) = v0 * t + (1/2) * g * t^2 + y0
+
+
+      Substituting the values given in the problem, we get:
+
+
+      y(t) = (30)(t) + (1/2)(-32)(t)^2 + 3
+
+
+      Now, let''s simplify the equation:
+
+
+      y(t) = 30t - 16t^2 + 3
+
+
+      This is the final solution for the height of the ball as a function of time.'
+model-index:
+- name: Hercules-2.0-Mistral-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: 61.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-2.0-Mistral-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: 83.69
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-2.0-Mistral-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: 63.47
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-2.0-Mistral-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: 43.97
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-2.0-Mistral-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: 79.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-2.0-Mistral-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: 44.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-2.0-Mistral-7B
+      name: Open LLM Leaderboard
 ---
 # Model Card: Hercules-2.0-Mistral-7B
 
@@ -94,4 +232,17 @@ This model was fine-tuned using the TPU-Alignment repository. https://github.com
 
 # Quants
 
-exl2 by @bartowski https://huggingface.co/bartowski/Hercules-2.0-Mistral-7B-exl2
+exl2 by @bartowski https://huggingface.co/bartowski/Hercules-2.0-Mistral-7B-exl2
+# [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_Locutusque__Hercules-2.0-Mistral-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |62.69|
+|AI2 Reasoning Challenge (25-Shot)|61.09|
+|HellaSwag (10-Shot)              |83.69|
+|MMLU (5-Shot)                    |63.47|
+|TruthfulQA (0-shot)              |43.97|
+|Winogrande (5-shot)              |79.48|
+|GSM8k (5-shot)                   |44.43|
+