Adding Evaluation Results (#1)

- Adding Evaluation Results (11db0855c5f29fd669fde6744d9fef6a0951d024)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,12 +1,107 @@
 ---
-license: mit
 language:
 - en
+license: mit
+library_name: transformers
 datasets:
 - TIGER-Lab/WebInstructSub
 metrics:
 - accuracy
-library_name: transformers
+model-index:
+- name: MAmmoTH2-7B-Plus
+  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: 55.75
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TIGER-Lab/MAmmoTH2-7B-Plus
+      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: 18.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TIGER-Lab/MAmmoTH2-7B-Plus
+      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: 16.09
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TIGER-Lab/MAmmoTH2-7B-Plus
+      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: 4.03
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TIGER-Lab/MAmmoTH2-7B-Plus
+      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: 10.11
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TIGER-Lab/MAmmoTH2-7B-Plus
+      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: 22.41
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TIGER-Lab/MAmmoTH2-7B-Plus
+      name: Open LLM Leaderboard
 ---
 # 🦣 MAmmoTH2: Scaling Instructions from the Web
 
@@ -66,4 +161,17 @@ If you use the models, data, or code from this project, please cite the original
   journal={arXiv preprint arXiv:2405.03548},
   year={2024}
 }
-```
+```
+# [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_TIGER-Lab__MAmmoTH2-7B-Plus)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |21.22|
+|IFEval (0-Shot)    |55.75|
+|BBH (3-Shot)       |18.93|
+|MATH Lvl 5 (4-Shot)|16.09|
+|GPQA (0-shot)      | 4.03|
+|MuSR (0-shot)      |10.11|
+|MMLU-PRO (5-shot)  |22.41|
+