Adding Evaluation Results

README.md

@@ -1,8 +1,6 @@
 ---
-license_name: tongyi-qianwen-research
-license_link: https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat/raw/main/LICENSE
-library_name: transformers
 license: other
+library_name: transformers
 tags:
 - finetune
 - synthetic data
@@ -11,6 +9,111 @@ tags:
 - COT
 datasets:
 - kaist-ai/CoT-Collection
+license_name: tongyi-qianwen-research
+license_link: https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat/raw/main/LICENSE
+model-index:
+- name: Reyna-CoT-4B-v0.1
+  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: 44.71
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/Reyna-CoT-4B-v0.1
+      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: 71.12
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/Reyna-CoT-4B-v0.1
+      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: 55.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/Reyna-CoT-4B-v0.1
+      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: 43.09
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/Reyna-CoT-4B-v0.1
+      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: 67.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/Reyna-CoT-4B-v0.1
+      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: 16.91
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/Reyna-CoT-4B-v0.1
+      name: Open LLM Leaderboard
 ---
 
 ![Reyna aloobun qwen4B](https://i.imgur.com/QfbOY6c.jpeg)
@@ -83,4 +186,17 @@ op = model.generate(
 ## Output:
 >She would have 8 x 9 = 72 flowers in total.
 >She would have 72 / 12 = 6 bunches of flowers with 12 flowers in each bunch.
->Therefore, the answer is 6.<|endoftext|>
+>Therefore, the answer is 6.<|endoftext|>
+# [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_aloobun__Reyna-CoT-4B-v0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |49.91|
+|AI2 Reasoning Challenge (25-Shot)|44.71|
+|HellaSwag (10-Shot)              |71.12|
+|MMLU (5-Shot)                    |55.90|
+|TruthfulQA (0-shot)              |43.09|
+|Winogrande (5-shot)              |67.72|
+|GSM8k (5-shot)                   |16.91|
+