Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
+language:
+- en
+license: cc-by-nc-4.0
 datasets:
 - c-s-ale/alpaca-gpt4-data
 - Open-Orca/OpenOrca
 - Intel/orca_dpo_pairs
 - allenai/ultrafeedback_binarized_cleaned
-language:
-- en
-license: cc-by-nc-4.0
 base_model:
-  - upstage/SOLAR-10.7B-v1.0
+- upstage/SOLAR-10.7B-v1.0
+model-index:
+- name: SOLAR-10.7B-Instruct-v1.0
+  results:
+  - 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: 71.08
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=upstage/SOLAR-10.7B-Instruct-v1.0
+      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: 88.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=upstage/SOLAR-10.7B-Instruct-v1.0
+      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: 66.21
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=upstage/SOLAR-10.7B-Instruct-v1.0
+      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: 71.43
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=upstage/SOLAR-10.7B-Instruct-v1.0
+      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: 83.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=upstage/SOLAR-10.7B-Instruct-v1.0
+      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: 64.75
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=upstage/SOLAR-10.7B-Instruct-v1.0
+      name: Open LLM Leaderboard
 ---
 
 <p align="left">
@@ -180,4 +283,17 @@ Please cite this model using this format.
 Upstage is creating the best LLM and DocAI. Please find more information at https://upstage.ai 
 
 ### **Contact Us** ###
-Any questions and suggestions, please use the discussion tab. If you want to contact us directly, drop an email to [contact@upstage.ai](mailto:contact@upstage.ai)
+Any questions and suggestions, please use the discussion tab. If you want to contact us directly, drop an email to [contact@upstage.ai](mailto:contact@upstage.ai)
+# [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_upstage__SOLAR-10.7B-Instruct-v1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.20|
+|AI2 Reasoning Challenge (25-Shot)|71.08|
+|HellaSwag (10-Shot)              |88.16|
+|MMLU (5-Shot)                    |66.21|
+|TruthfulQA (0-shot)              |71.43|
+|Winogrande (5-shot)              |83.58|
+|GSM8k (5-shot)                   |64.75|
+