Adding Evaluation Results

README.md

@@ -1,9 +1,125 @@
 ---
-license: apache-2.0
 language:
 - en
+license: apache-2.0
 datasets:
 - Open-Orca/FLAN
+model-index:
+- name: Llama-Flan-XL2base
+  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: 20.65
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sayan01/Llama-Flan-XL2base
+      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: 25.33
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sayan01/Llama-Flan-XL2base
+      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: 23.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sayan01/Llama-Flan-XL2base
+      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: 50.58
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sayan01/Llama-Flan-XL2base
+      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: 50.91
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sayan01/Llama-Flan-XL2base
+      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=Sayan01/Llama-Flan-XL2base
+      name: Open LLM Leaderboard
 ---
 
-This is a 230M parameter Small Llama model distilled from the Original one. The model is distilled on OpenOrca's FLAN dataset. The distillation ran over 160000 random samples of FLAN dataset. It is free to download. Also, it is a work in progress, so please use it at your own risk
+This is a 230M parameter Small Llama model distilled from the Original one. The model is distilled on OpenOrca's FLAN dataset. The distillation ran over 160000 random samples of FLAN dataset. It is free to download. Also, it is a work in progress, so please use it at your own risk
+# [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_Sayan01__Llama-Flan-XL2base)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |28.44|
+|AI2 Reasoning Challenge (25-Shot)|20.65|
+|HellaSwag (10-Shot)              |25.33|
+|MMLU (5-Shot)                    |23.19|
+|TruthfulQA (0-shot)              |50.58|
+|Winogrande (5-shot)              |50.91|
+|GSM8k (5-shot)                   | 0.00|
+