Adding Evaluation Results

README.md

@@ -1,5 +1,108 @@
 ---
 license: llama2
+model-index:
+- name: LLaMA-Pro-8B-Instruct
+  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: 52.99
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TencentARC/LLaMA-Pro-8B-Instruct
+      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: 76.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TencentARC/LLaMA-Pro-8B-Instruct
+      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: 52.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TencentARC/LLaMA-Pro-8B-Instruct
+      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: 49.43
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TencentARC/LLaMA-Pro-8B-Instruct
+      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/HuggingFaceH4/open_llm_leaderboard?query=TencentARC/LLaMA-Pro-8B-Instruct
+      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: 44.2
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TencentARC/LLaMA-Pro-8B-Instruct
+      name: Open LLM Leaderboard
 ---
 
 # LLaMA-PRO-Instruct Model Card
@@ -20,4 +123,17 @@ It surpasses its predecessors in the LLaMA series, especially in code domains, d
 Despite advancements, it may encounter difficulties in highly niche or nuanced tasks.
 
 ## Ethical Considerations
-Users are advised to consider inherent biases and responsibly manage its application across various fields.
+Users are advised to consider inherent biases and responsibly manage its application across various fields.
+# [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_TencentARC__LLaMA-Pro-8B-Instruct)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |58.06|
+|AI2 Reasoning Challenge (25-Shot)|52.99|
+|HellaSwag (10-Shot)              |76.98|
+|MMLU (5-Shot)                    |52.58|
+|TruthfulQA (0-shot)              |49.43|
+|Winogrande (5-shot)              |72.22|
+|GSM8k (5-shot)                   |44.20|
+