Adding Evaluation Results

README.md

@@ -1,9 +1,104 @@
 ---
+language:
+- en
 license: llama3.1
 datasets:
 - BAAI/Infinity-Instruct
-language:
-- en
+model-index:
+- name: Infinity-Instruct-7M-Gen-Llama3_1-8B
+  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: 61.32
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8B
+      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: 30.89
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8B
+      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: 9.74
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8B
+      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: 5.7
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8B
+      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: 5.3
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8B
+      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: 24.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8B
+      name: Open LLM Leaderboard
 ---
 # Infinity Instruct
 
@@ -145,4 +240,17 @@ Our paper, detailing the development and features of the **Infinity Instruct** d
   journal={arXiv preprint arXiv:2406.XXXX},
   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_BAAI__Infinity-Instruct-7M-Gen-Llama3_1-8B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.94|
+|IFEval (0-Shot)    |61.32|
+|BBH (3-Shot)       |30.89|
+|MATH Lvl 5 (4-Shot)| 9.74|
+|GPQA (0-shot)      | 5.70|
+|MuSR (0-shot)      | 5.30|
+|MMLU-PRO (5-shot)  |24.71|
+