From 847547f1586e0cf2bed5b20a5566b85f286d52dc Mon Sep 17 00:00:00 2001
From: Open LLM Leaderboard PR Bot
 <leaderboard-pr-bot@users.noreply.huggingface.co>
Date: Wed, 12 Jun 2024 19:03:00 +0000
Subject: [PATCH] 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 | 124 ++++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 120 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index b2d85ca..1e92ab4 100644
--- a/README.md
+++ b/README.md
@@ -1,12 +1,115 @@
 ---
-license: mit
-license_link: https://huggingface.co/microsoft/phi-1_5/resolve/main/LICENSE
 language:
 - en
-pipeline_tag: text-generation
+license: mit
 tags:
 - nlp
 - code
+license_link: https://huggingface.co/microsoft/phi-1_5/resolve/main/LICENSE
+pipeline_tag: text-generation
+model-index:
+- name: phi-1_5
+  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: 52.9
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=microsoft/phi-1_5
+      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: 63.79
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=microsoft/phi-1_5
+      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: 43.89
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=microsoft/phi-1_5
+      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: 40.89
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=microsoft/phi-1_5
+      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: 72.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=microsoft/phi-1_5
+      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: 12.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=microsoft/phi-1_5
+      name: Open LLM Leaderboard
 ---
 ## Model Summary
 
@@ -158,4 +261,17 @@ You can find the paper at https://arxiv.org/abs/2309.05463. Please cite as:
 
 ## Trademarks
 
-This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.
\ No newline at end of file
+This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.
+# [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_microsoft__phi-1_5)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |47.69|
+|AI2 Reasoning Challenge (25-Shot)|52.90|
+|HellaSwag (10-Shot)              |63.79|
+|MMLU (5-Shot)                    |43.89|
+|TruthfulQA (0-shot)              |40.89|
+|Winogrande (5-shot)              |72.22|
+|GSM8k (5-shot)                   |12.43|
+