Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,17 +1,17 @@
 ---
-license: apache-2.0
-datasets:
-- Locutusque/hercules-v1.0
-- Open-Orca/SlimOrca-Dedup
 language:
 - en
-base_model: Locutusque/TinyMistral-248M-v2.5
+license: apache-2.0
 tags:
 - chemistry
 - biology
 - not-for-all-audiences
 - merge
 - code
+datasets:
+- Locutusque/hercules-v1.0
+- Open-Orca/SlimOrca-Dedup
+base_model: Locutusque/TinyMistral-248M-v2.5
 inference:
   parameters:
     do_sample: true
@@ -25,7 +25,116 @@ inference:
     no_repeat_ngram_size: 5
     epsilon_cutoff: 0.002
 widget:
-  - text: "<|im_start|>user\nWrite me a Python program that calculates the factorial of n. <|im_end|>\n<|im_start|>assistant\n"
+- text: '<|im_start|>user
+
+    Write me a Python program that calculates the factorial of n. <|im_end|>
+
+    <|im_start|>assistant
+
+    '
+model-index:
+- name: TinyMistral-248M-v2.5-Instruct
+  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: 22.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5-Instruct
+      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: 27.6
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5-Instruct
+      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: 23.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5-Instruct
+      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: 44.21
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5-Instruct
+      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: 48.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5-Instruct
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5-Instruct
+      name: Open LLM Leaderboard
 ---
 # Model description
 Fine-tuned Locutusque/TinyMistral-248m-v2.5 on SlimOrca-Dedup and Hercules-v1.0. Averaged a loss of 1.5 during training. This model's performance is excellent considering it's size. 
@@ -34,4 +143,17 @@ This model may output X-rated content. You and you alone are responsible for dow
 
 You can use the ChatML prompt format for this model.
 # Evaluation
-This model will be submitted to the Open LLM Leaderboard. 
+This model will be submitted to the Open LLM Leaderboard. 
+# [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__TinyMistral-248M-v2.5-Instruct)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |27.70|
+|AI2 Reasoning Challenge (25-Shot)|22.27|
+|HellaSwag (10-Shot)              |27.60|
+|MMLU (5-Shot)                    |23.90|
+|TruthfulQA (0-shot)              |44.21|
+|Winogrande (5-shot)              |48.22|
+|GSM8k (5-shot)                   | 0.00|
+