Adding Evaluation Results

README.md

@@ -8,6 +8,105 @@ datasets:
 base_model:
 - allenai/Llama-3.1-Tulu-3-8B-SFT
 library_name: transformers
+model-index:
+- name: Llama-3.1-Tulu-3-8B-DPO
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: wis-k/instruction-following-eval
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 80.29
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=allenai%2FLlama-3.1-Tulu-3-8B-DPO
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: SaylorTwift/bbh
+      split: test
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 17.43
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=allenai%2FLlama-3.1-Tulu-3-8B-DPO
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: lighteval/MATH-Hard
+      split: test
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 18.58
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=allenai%2FLlama-3.1-Tulu-3-8B-DPO
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 5.82
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=allenai%2FLlama-3.1-Tulu-3-8B-DPO
+      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: 10.52
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=allenai%2FLlama-3.1-Tulu-3-8B-DPO
+      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: 21.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=allenai%2FLlama-3.1-Tulu-3-8B-DPO
+      name: Open LLM Leaderboard
 ---
 
 <img src="https://huggingface.co/datasets/allenai/blog-images/resolve/main/tulu3/Tulu3-logo.png" alt="Tulu 3 banner" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
@@ -179,4 +278,18 @@ If Tülu3 or any of the related materials were helpful to your work, please cite
   year = {2024},
   email = {tulu@allenai.org}
 }
-```
+```
+# [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/allenai__Llama-3.1-Tulu-3-8B-DPO-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=allenai%2FLlama-3.1-Tulu-3-8B-DPO&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    25.62|
+|IFEval (0-Shot)    |    80.29|
+|BBH (3-Shot)       |    17.43|
+|MATH Lvl 5 (4-Shot)|    18.58|
+|GPQA (0-shot)      |     5.82|
+|MuSR (0-shot)      |    10.52|
+|MMLU-PRO (5-shot)  |    21.09|
+