Adding Evaluation Results (#10)

- Adding Evaluation Results (6aaaa93f7005cc262c4d2caed59953ed42d0b1c9)


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

README.md

@@ -15,7 +15,6 @@ tags:
 - code
 - chatml
 base_model: microsoft/Phi-3-mini-4k-instruct
-model_name: Phi-3-mini-4k-instruct-v0.3
 pipeline_tag: text-generation
 inference: false
 model_creator: MaziyarPanahi
@@ -123,6 +122,98 @@ model-index:
     source:
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
       name: Open LLM Leaderboard
+  - 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: 49.26
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
+      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: 37.66
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
+      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: 2.95
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
+      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: 9.06
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
+      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: 7.75
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
+      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: 31.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
+      name: Open LLM Leaderboard
 ---
 
 <img src="./phi-3-instruct.webp" alt="Phi-3 Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
@@ -228,3 +319,17 @@ print(output[0]['generated_text'])
 
 
 ```
+
+# [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_MaziyarPanahi__Phi-3-mini-4k-instruct-v0.3)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |23.38|
+|IFEval (0-Shot)    |49.26|
+|BBH (3-Shot)       |37.66|
+|MATH Lvl 5 (4-Shot)| 2.95|
+|GPQA (0-shot)      | 9.06|
+|MuSR (0-shot)      | 7.75|
+|MMLU-PRO (5-shot)  |31.42|
+