Adding Evaluation Results

README.md

@@ -1,6 +1,109 @@
 ---
-pipeline_tag: text-generation
 license: other
+pipeline_tag: text-generation
+model-index:
+- name: internlm2-7b
+  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: 58.02
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=internlm/internlm2-7b
+      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: 81.24
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=internlm/internlm2-7b
+      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: 65.24
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=internlm/internlm2-7b
+      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: 48.73
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=internlm/internlm2-7b
+      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: 83.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=internlm/internlm2-7b
+      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: 63.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=internlm/internlm2-7b
+      name: Open LLM Leaderboard
 ---
 # InternLM 
 
@@ -163,4 +266,17 @@ print(output)
 
 ## 开源许可证
 
-本仓库的代码依照 Apache-2.0 协议开源。模型权重对学术研究完全开放，也可申请免费的商业使用授权（[申请表](https://wj.qq.com/s2/12725412/f7c1/)）。其他问题与合作请联系 <internlm@pjlab.org.cn>。
+本仓库的代码依照 Apache-2.0 协议开源。模型权重对学术研究完全开放，也可申请免费的商业使用授权（[申请表](https://wj.qq.com/s2/12725412/f7c1/)）。其他问题与合作请联系 <internlm@pjlab.org.cn>。
+# [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_internlm__internlm2-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |66.68|
+|AI2 Reasoning Challenge (25-Shot)|58.02|
+|HellaSwag (10-Shot)              |81.24|
+|MMLU (5-Shot)                    |65.24|
+|TruthfulQA (0-shot)              |48.73|
+|Winogrande (5-shot)              |83.82|
+|GSM8k (5-shot)                   |63.00|
+