Adding Evaluation Results

README.md

@@ -1,17 +1,120 @@
 ---
+language:
+- en
+license: apache-2.0
+library_name: transformers
 tags:
 - text2text-generation
 datasets:
 - kaist-ai/Feedback-Collection
-license: apache-2.0
-language:
-- en
-pipeline_tag: text2text-generation
-library_name: transformers
 metrics:
 - pearsonr
 - spearmanr
 - accuracy
+pipeline_tag: text2text-generation
+model-index:
+- name: prometheus-13b-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: 53.24
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai/prometheus-13b-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: 80.75
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai/prometheus-13b-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: 51.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai/prometheus-13b-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: 45.66
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai/prometheus-13b-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: 73.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai/prometheus-13b-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: 31.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai/prometheus-13b-v1.0
+      name: Open LLM Leaderboard
 ---
 ## Links for Reference
 
@@ -207,4 +310,17 @@ If you find the following model helpful, please consider citing our paper!
     archivePrefix={arXiv},
     primaryClass={cs.CL}
 }
-```
+```
+# [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_kaist-ai__prometheus-13b-v1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |56.09|
+|AI2 Reasoning Challenge (25-Shot)|53.24|
+|HellaSwag (10-Shot)              |80.75|
+|MMLU (5-Shot)                    |51.49|
+|TruthfulQA (0-shot)              |45.66|
+|Winogrande (5-shot)              |73.72|
+|GSM8k (5-shot)                   |31.69|
+