Adding Evaluation Results

README.md

@@ -1,16 +1,111 @@
 ---
-license: apache-2.0
 language:
 - en
+license: apache-2.0
+library_name: transformers
 tags:
 - moe
 - olmo
 - olmoe
-co2_eq_emissions: 1
+base_model: allenai/OLMoE-1B-7B-0924-SFT
 datasets:
 - allenai/ultrafeedback_binarized_cleaned
-base_model: allenai/OLMoE-1B-7B-0924-SFT
-library_name: transformers
+co2_eq_emissions: 1
+model-index:
+- name: OLMoE-1B-7B-0924-Instruct
+  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: 46.52
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allenai/OLMoE-1B-7B-0924-Instruct
+      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: 14.57
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allenai/OLMoE-1B-7B-0924-Instruct
+      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: 0.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allenai/OLMoE-1B-7B-0924-Instruct
+      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: 2.35
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allenai/OLMoE-1B-7B-0924-Instruct
+      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: 6.07
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allenai/OLMoE-1B-7B-0924-Instruct
+      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: 9.73
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allenai/OLMoE-1B-7B-0924-Instruct
+      name: Open LLM Leaderboard
 ---
 
 <img alt="OLMoE Logo." src="olmoe-logo.png" width="250px">
@@ -93,4 +188,17 @@ Branches:
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2409.02060}, 
 }
-```
+```
+# [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__OLMoE-1B-7B-0924-Instruct)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |13.21|
+|IFEval (0-Shot)    |46.52|
+|BBH (3-Shot)       |14.57|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      | 2.35|
+|MuSR (0-shot)      | 6.07|
+|MMLU-PRO (5-shot)  | 9.73|
+