Adding Evaluation Results

README.md

@@ -1,18 +1,121 @@
 ---
+language:
+- en
 license: apache-2.0
+tags:
+- gpt2
+- dpo
+- code
 datasets:
 - HuggingFaceH4/ultrachat_200k
 - mlabonne/CodeLlama-2-20k
 - Intel/orca_dpo_pairs
 - Sharathhebbar24/Evol-Instruct-Code-80k-v1
 - Sharathhebbar24/sql-create-context
-language:
-- en
 pipeline_tag: text-generation
-tags:
-- gpt2
-- dpo
-- code
+model-index:
+- name: code_gpt2
+  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: 23.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/code_gpt2
+      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: 30.99
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/code_gpt2
+      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: 25.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/code_gpt2
+      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: 40.6
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/code_gpt2
+      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: 49.25
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/code_gpt2
+      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=Sharathhebbar24/code_gpt2
+      name: Open LLM Leaderboard
 ---
 
 This model is a finetuned version of [Sharathhebbar24/code_gpt2_mini_model](https://huggingface.co/Sharathhebbar24/code_gpt2_mini_model) using [Sharathhebbar24/Evol-Instruct-Code-80k-v1](https://huggingface.co/datasets/Sharathhebbar24/Evol-Instruct-Code-80k-v1)
@@ -47,4 +150,17 @@ prompt.
 >>> prompt = "Can you write a Linear search program in Python"
 >>> res = generate_text(prompt)
 >>> res
-```
+```
+# [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_Sharathhebbar24__code_gpt2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |28.19|
+|AI2 Reasoning Challenge (25-Shot)|23.29|
+|HellaSwag (10-Shot)              |30.99|
+|MMLU (5-Shot)                    |25.03|
+|TruthfulQA (0-shot)              |40.60|
+|Winogrande (5-shot)              |49.25|
+|GSM8k (5-shot)                   | 0.00|
+