Adding Evaluation Results

README.md

@@ -1,5 +1,100 @@
 ---
 license: llama3
+model-index:
+- name: Llama-3-8B-ProLong-512k-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: 41.3
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=princeton-nlp/Llama-3-8B-ProLong-512k-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: 28.44
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=princeton-nlp/Llama-3-8B-ProLong-512k-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: 4.46
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=princeton-nlp/Llama-3-8B-ProLong-512k-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: 2.24
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=princeton-nlp/Llama-3-8B-ProLong-512k-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: 11.66
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=princeton-nlp/Llama-3-8B-ProLong-512k-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: 24.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=princeton-nlp/Llama-3-8B-ProLong-512k-Instruct
+      name: Open LLM Leaderboard
 ---
 
 # princeton_nlp/Llama-3-8B-ProLong-512k-Instruct
@@ -273,4 +368,17 @@ If you find our model useful, please cite by
    year={2024},
    url="https://huggingface.co/princeton-nlp/Llama-3-8B-ProLong-64k-Instruct"
 }
-```
+```
+# [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_princeton-nlp__Llama-3-8B-ProLong-512k-Instruct)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |18.83|
+|IFEval (0-Shot)    |41.30|
+|BBH (3-Shot)       |28.44|
+|MATH Lvl 5 (4-Shot)| 4.46|
+|GPQA (0-shot)      | 2.24|
+|MuSR (0-shot)      |11.66|
+|MMLU-PRO (5-shot)  |24.90|
+