Adding Evaluation Results

This is an automated PR created with https://huggingface.co./spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co./spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,4 +1,10 @@
 ---
+license: bigcode-openrail-m
+library_name: transformers
+tags:
+- code
+datasets:
+- bigcode/the-stack-v2-train
 pipeline_tag: text-generation
 inference:
   parameters:
@@ -8,12 +14,6 @@ widget:
 - text: 'def print_hello_world():'
   example_title: Hello world
   group: Python
-datasets:
-- bigcode/the-stack-v2-train
-license: bigcode-openrail-m
-library_name: transformers
-tags:
-- code
 model-index:
 - name: starcoder2-15b
   results:
@@ -65,6 +65,98 @@ model-index:
     metrics:
     - type: edit-smiliarity
       value: 74.08
+  - 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: 27.35
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bigcode/starcoder2-15b
+      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: 20.24
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bigcode/starcoder2-15b
+      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: 4.83
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bigcode/starcoder2-15b
+      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: 2.91
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bigcode/starcoder2-15b
+      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: 2.93
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bigcode/starcoder2-15b
+      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: 15.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bigcode/starcoder2-15b
+      name: Open LLM Leaderboard
 ---
 
 # StarCoder2
@@ -212,4 +304,17 @@ The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can
       archivePrefix={arXiv},
       primaryClass={cs.SE}
 }
-```
+```
+# [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_bigcode__starcoder2-15b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |12.21|
+|IFEval (0-Shot)    |27.35|
+|BBH (3-Shot)       |20.24|
+|MATH Lvl 5 (4-Shot)| 4.83|
+|GPQA (0-shot)      | 2.91|
+|MuSR (0-shot)      | 2.93|
+|MMLU-PRO (5-shot)  |15.03|
+