Adding Evaluation Results

README.md

@@ -3,6 +3,109 @@ license: apache-2.0
 datasets:
 - snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset
 pipeline_tag: text-generation
+model-index:
+- name: Snorkel-Mistral-PairRM-DPO
+  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: 66.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=snorkelai/Snorkel-Mistral-PairRM-DPO
+      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: 85.64
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=snorkelai/Snorkel-Mistral-PairRM-DPO
+      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: 60.83
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=snorkelai/Snorkel-Mistral-PairRM-DPO
+      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: 70.86
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=snorkelai/Snorkel-Mistral-PairRM-DPO
+      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: 77.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=snorkelai/Snorkel-Mistral-PairRM-DPO
+      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: 36.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=snorkelai/Snorkel-Mistral-PairRM-DPO
+      name: Open LLM Leaderboard
 ---
 
 Read our release blog here: [Snorkel AI Blog](https://snorkel.ai/new-benchmark-results-demonstrate-value-of-snorkel-ai-approach-to-llm-alignment/)
@@ -118,4 +221,17 @@ Snorkel-Mistral-PairRM-DPO GGUF model version: from [andrew-cartwheel](https://h
 Thanks to the mentioned community members for providing the GGUF model versions.
 
 ### The Snorkel AI Team
-Hoang Tran, Chris Glaze, Braden Hancock
+Hoang Tran, Chris Glaze, Braden Hancock
+# [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_snorkelai__Snorkel-Mistral-PairRM-DPO)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |66.31|
+|AI2 Reasoning Challenge (25-Shot)|66.04|
+|HellaSwag (10-Shot)              |85.64|
+|MMLU (5-Shot)                    |60.83|
+|TruthfulQA (0-shot)              |70.86|
+|Winogrande (5-shot)              |77.74|
+|GSM8k (5-shot)                   |36.77|
+