Adding Evaluation Results

README.md

@@ -1,13 +1,116 @@
 ---
+language:
+- en
+license: gemma
 library_name: transformers
 tags:
 - code
-license: gemma
 datasets:
 - LimYeri/LeetCode_with_Solutions
-language:
-- en
 pipeline_tag: text-generation
+model-index:
+- name: CodeMind-Gemma-7B-QLoRA-4bit
+  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: 23.21
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=LimYeri/CodeMind-Gemma-7B-QLoRA-4bit
+      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: 31.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=LimYeri/CodeMind-Gemma-7B-QLoRA-4bit
+      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: 23.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=LimYeri/CodeMind-Gemma-7B-QLoRA-4bit
+      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: 0.0
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=LimYeri/CodeMind-Gemma-7B-QLoRA-4bit
+      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: 60.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=LimYeri/CodeMind-Gemma-7B-QLoRA-4bit
+      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=LimYeri/CodeMind-Gemma-7B-QLoRA-4bit
+      name: Open LLM Leaderboard
 ---
 
 # CodeMind
@@ -109,4 +212,17 @@ print(result)
 ## Ethical Considerations
 - The model should be used as a supportive tool for learning and problem-solving, not as a substitute for human expertise and critical thinking.
 - Users should be aware that the model's responses are generated based on patterns in the training data and may not always be accurate, complete, or up to date.
-- The model should not be relied upon for making critical decisions or solving real-world problems without thorough validation and testing.
+- The model should not be relied upon for making critical decisions or solving real-world problems without thorough validation and testing.
+# [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_LimYeri__CodeMind-Gemma-7B-QLoRA-4bit)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |22.97|
+|AI2 Reasoning Challenge (25-Shot)|23.21|
+|HellaSwag (10-Shot)              |31.17|
+|MMLU (5-Shot)                    |23.12|
+|TruthfulQA (0-shot)              | 0.00|
+|Winogrande (5-shot)              |60.30|
+|GSM8k (5-shot)                   | 0.00|
+