Adding Evaluation Results

README.md

@@ -1,19 +1,121 @@
 ---
-license: other
-license_name: qwen
-license_link: >-
-  https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT
 language:
 - en
 - zh
+license: other
 library_name: transformers
-pipeline_tag: text-generation
-inference: false
 tags:
 - mistral
 - qwen
 - qwen1.5
 - qwen2
+license_name: qwen
+license_link: https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT
+pipeline_tag: text-generation
+inference: false
+model-index:
+- name: Qwen1.5-7B-Chat_mistral
+  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: 24.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Minami-su/Qwen1.5-7B-Chat_mistral
+      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: 26.69
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Minami-su/Qwen1.5-7B-Chat_mistral
+      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: 25.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Minami-su/Qwen1.5-7B-Chat_mistral
+      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: 52.33
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Minami-su/Qwen1.5-7B-Chat_mistral
+      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: 53.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Minami-su/Qwen1.5-7B-Chat_mistral
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Minami-su/Qwen1.5-7B-Chat_mistral
+      name: Open LLM Leaderboard
 ---
 This is the Mistral version of [Qwen1.5-7B-Chat](https://huggingface.co/Qwen/Qwen1.5-7B-Chat) model by Alibaba Cloud.
 The original codebase can be found at: (https://github.com/hiyouga/LLaMA-Factory/blob/main/tests/llamafy_qwen.py).
@@ -82,4 +184,17 @@ hf-causal (pretrained=Qwen1.5-7B-Chat_mistral), limit: None, provide_description
 |             |       |mc2     |0.5161|±  |0.0159|
 |winogrande   |      0|acc     |0.6306|±  |0.0136|
 ```
-```
+```
+# [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_Minami-su__Qwen1.5-7B-Chat_mistral)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |30.49|
+|AI2 Reasoning Challenge (25-Shot)|24.49|
+|HellaSwag (10-Shot)              |26.69|
+|MMLU (5-Shot)                    |25.78|
+|TruthfulQA (0-shot)              |52.33|
+|Winogrande (5-shot)              |53.67|
+|GSM8k (5-shot)                   | 0.00|
+