Adding Evaluation Results

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 +65,106 @@ model-index:
     metrics:
     - type: edit-smiliarity
       value: 74.08
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 47.35
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bigcode/starcoder2-15b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 64.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bigcode/starcoder2-15b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 51.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bigcode/starcoder2-15b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 37.87
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bigcode/starcoder2-15b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 63.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bigcode/starcoder2-15b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 52.24
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bigcode/starcoder2-15b
+      name: Open LLM Leaderboard
 ---
 
 # StarCoder2
@@ -212,4 +312,17 @@ 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/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_bigcode__starcoder2-15b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |52.79|
+|AI2 Reasoning Challenge (25-Shot)|47.35|
+|HellaSwag (10-Shot)              |64.09|
+|MMLU (5-Shot)                    |51.35|
+|TruthfulQA (0-shot)              |37.87|
+|Winogrande (5-shot)              |63.85|
+|GSM8k (5-shot)                   |52.24|
+