Adding Evaluation Results

README.md

@@ -1,13 +1,115 @@
 ---
-license: other
-license_name: tongyi-qianwen
-license_link: >-
-  https://huggingface.co/Qwen/Qwen1.5-14B-Chat/blob/main/LICENSE
 language:
 - en
-pipeline_tag: text-generation
+license: other
 tags:
 - chat
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/Qwen/Qwen1.5-14B-Chat/blob/main/LICENSE
+pipeline_tag: text-generation
+model-index:
+- name: Qwen1.5-14B-Chat
+  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: 58.79
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Qwen/Qwen1.5-14B-Chat
+      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: 82.33
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Qwen/Qwen1.5-14B-Chat
+      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: 68.52
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Qwen/Qwen1.5-14B-Chat
+      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: 60.38
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Qwen/Qwen1.5-14B-Chat
+      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: 73.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Qwen/Qwen1.5-14B-Chat
+      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: 30.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Qwen/Qwen1.5-14B-Chat
+      name: Open LLM Leaderboard
 ---
 
 # Qwen1.5-14B-Chat
@@ -95,4 +197,17 @@ If you find our work helpful, feel free to give us a cite.
   journal={arXiv preprint arXiv:2309.16609},
   year={2023}
 }
-```
+```
+# [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_Qwen__Qwen1.5-14B-Chat)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |62.37|
+|AI2 Reasoning Challenge (25-Shot)|58.79|
+|HellaSwag (10-Shot)              |82.33|
+|MMLU (5-Shot)                    |68.52|
+|TruthfulQA (0-shot)              |60.38|
+|Winogrande (5-shot)              |73.32|
+|GSM8k (5-shot)                   |30.86|
+