Adding Evaluation Results

README.md

@@ -1,17 +1,112 @@
 ---
-license: mit
-license_link: https://huggingface.co/microsoft/Phi-3.5-mini-instruct/resolve/main/LICENSE
 language:
 - multilingual
-pipeline_tag: text-generation
+license: mit
+library_name: transformers
 tags:
 - nlp
 - code
+license_link: https://huggingface.co/microsoft/Phi-3.5-mini-instruct/resolve/main/LICENSE
+pipeline_tag: text-generation
 widget:
 - messages:
   - role: user
     content: Can you provide ways to eat combinations of bananas and dragonfruits?
-library_name: transformers
+model-index:
+- name: Phi-3.5-mini-instruct
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 57.75
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=microsoft/Phi-3.5-mini-instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 36.75
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=microsoft/Phi-3.5-mini-instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 14.95
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=microsoft/Phi-3.5-mini-instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 11.97
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=microsoft/Phi-3.5-mini-instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 10.1
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=microsoft/Phi-3.5-mini-instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 32.91
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=microsoft/Phi-3.5-mini-instruct
+      name: Open LLM Leaderboard
 ---
 
 ## Model Summary
@@ -373,4 +468,17 @@ This project may contain trademarks or logos for projects, products, or services
 |-----------|-----------------------|---------------------------------------|--------------------------|---------------------------|------------------|----------------|------------------|-------------------------------|
 | English   | 94.6                  | 94.6                                  | 85.6                     | 94.4                      | 37.6             | 63.8           | 92.0             | 98.2                          |
 | Italian   | 86.8                  | 84.8                                  | 76.8                     | 83.2                      | 16.2             | 37.2           | 85.6             | 97.6                          |
-| Turkish   | 58.6                  | 57.2                                  | 61.6                     | 56.6                      | 38.4             | 60.2           | 91.4             | 94.6                          |
+| Turkish   | 58.6                  | 57.2                                  | 61.6                     | 56.6                      | 38.4             | 60.2           | 91.4             | 94.6                          |
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_microsoft__Phi-3.5-mini-instruct)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |27.40|
+|IFEval (0-Shot)    |57.75|
+|BBH (3-Shot)       |36.75|
+|MATH Lvl 5 (4-Shot)|14.95|
+|GPQA (0-shot)      |11.97|
+|MuSR (0-shot)      |10.10|
+|MMLU-PRO (5-shot)  |32.91|
+