Adding Evaluation Results

README.md

@@ -6,10 +6,113 @@ tags:
 - nlp
 - code
 - mlx
-license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE
 datasets:
 - teknium/openhermes
+license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE
 pipeline_tag: text-generation
+model-index:
+- name: phi-2-openhermes-30k
+  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: 61.01
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=marcel/phi-2-openhermes-30k
+      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: 74.72
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=marcel/phi-2-openhermes-30k
+      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: 57.17
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=marcel/phi-2-openhermes-30k
+      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: 45.38
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=marcel/phi-2-openhermes-30k
+      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: 74.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=marcel/phi-2-openhermes-30k
+      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: 49.05
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=marcel/phi-2-openhermes-30k
+      name: Open LLM Leaderboard
 ---
 
 # marcel/phi-2-openhermes-30k
@@ -48,3 +151,17 @@ outputs = model.generate(
 )
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
+
+# [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_marcel__phi-2-openhermes-30k)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |60.37|
+|AI2 Reasoning Challenge (25-Shot)|61.01|
+|HellaSwag (10-Shot)              |74.72|
+|MMLU (5-Shot)                    |57.17|
+|TruthfulQA (0-shot)              |45.38|
+|Winogrande (5-shot)              |74.90|
+|GSM8k (5-shot)                   |49.05|
+