Adding Evaluation Results (#1)

- Adding Evaluation Results (81c9d05ffa06de9259e4c19b81b0940e37347e10)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,10 +1,113 @@
 ---
-license: cc-by-nc-sa-4.0
-pipeline_tag: text-generation
 language:
-  - en
+- en
+license: cc-by-nc-sa-4.0
 tags:
 - finetuned
+pipeline_tag: text-generation
+model-index:
+- name: zoyllm-7b-slimorca
+  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: 50.6
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tlphams/zoyllm-7b-slimorca
+      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: 72.12
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tlphams/zoyllm-7b-slimorca
+      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: 48.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tlphams/zoyllm-7b-slimorca
+      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: 49.13
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tlphams/zoyllm-7b-slimorca
+      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: 67.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tlphams/zoyllm-7b-slimorca
+      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: 20.7
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tlphams/zoyllm-7b-slimorca
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for ZoyLLM-7B-SlimOrca
@@ -71,4 +174,17 @@ Ensure you are utilizing a stable version of Transformers, 4.34.0 or newer.
 
 ## 6. The Zoy AI Team
  
-Pham Tung Lam, Nguyen Duc Nhan.
+Pham Tung Lam, Nguyen Duc Nhan.
+# [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_tlphams__zoyllm-7b-slimorca)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |51.44|
+|AI2 Reasoning Challenge (25-Shot)|50.60|
+|HellaSwag (10-Shot)              |72.12|
+|MMLU (5-Shot)                    |48.78|
+|TruthfulQA (0-shot)              |49.13|
+|Winogrande (5-shot)              |67.32|
+|GSM8k (5-shot)                   |20.70|
+