Adding Evaluation Results

README.md

@@ -1,13 +1,108 @@
 ---
-license: llama3.1
 language:
 - en
-pipeline_tag: text-generation
-datasets:
-- allenai/tulu-3-sft-mixture
+license: llama3.1
+library_name: transformers
 base_model:
 - meta-llama/Llama-3.1-70B
-library_name: transformers
+datasets:
+- allenai/tulu-3-sft-mixture
+pipeline_tag: text-generation
+model-index:
+- name: Llama-3.1-Tulu-3-70B-SFT
+  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: 80.51
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allenai/Llama-3.1-Tulu-3-70B-SFT
+      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: 42.02
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allenai/Llama-3.1-Tulu-3-70B-SFT
+      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: 32.4
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allenai/Llama-3.1-Tulu-3-70B-SFT
+      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: 12.64
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allenai/Llama-3.1-Tulu-3-70B-SFT
+      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: 24.49
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allenai/Llama-3.1-Tulu-3-70B-SFT
+      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: 40.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allenai/Llama-3.1-Tulu-3-70B-SFT
+      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'"/>
@@ -177,4 +272,17 @@ 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/details_allenai__Llama-3.1-Tulu-3-70B-SFT)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |38.72|
+|IFEval (0-Shot)    |80.51|
+|BBH (3-Shot)       |42.02|
+|MATH Lvl 5 (4-Shot)|32.40|
+|GPQA (0-shot)      |12.64|
+|MuSR (0-shot)      |24.49|
+|MMLU-PRO (5-shot)  |40.27|
+