Adding Evaluation Results

README.md

@@ -1,26 +1,126 @@
 ---
-license: llama2
 language:
 - en
+license: llama2
 library_name: transformers
-pipeline_tag: text-generation
-model-index:
-  - name: CodeMate-v0.1
-    results:
-      - task:
-          type: text-generation
-        dataset:
-          name: HumanEval
-          type: openai_humaneval
-        metrics:
-          - name: pass@1
-            type: pass@1
-            value: 74.9%
-            verified: false
 tags:
 - CodeMate
 - Code
 - CodeLLaMa
+pipeline_tag: text-generation
+model-index:
+- name: CodeMate-v0.1
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEval
+      type: openai_humaneval
+    metrics:
+    - type: pass@1
+      value: 74.9%
+      name: pass@1
+      verified: false
+  - 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: 55.55
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=codemateai/CodeMate-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: 78.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=codemateai/CodeMate-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: 55.31
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=codemateai/CodeMate-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: 48.64
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=codemateai/CodeMate-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: 72.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=codemateai/CodeMate-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: 40.18
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=codemateai/CodeMate-v0.1
+      name: Open LLM Leaderboard
 ---
 
 
@@ -83,4 +183,17 @@ tokenizer = AutoTokenizer.from_pretrained(model_path)
 
 This model has undergone very limited testing. CodeMate recommends additional safety testing before any real-world deployments.
 
-For more information and updates, visit the [CodeMate website](https://codemate.ai).
+For more information and updates, visit the [CodeMate website](https://codemate.ai).
+# [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_codemateai__CodeMate-v0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |58.39|
+|AI2 Reasoning Challenge (25-Shot)|55.55|
+|HellaSwag (10-Shot)              |78.03|
+|MMLU (5-Shot)                    |55.31|
+|TruthfulQA (0-shot)              |48.64|
+|Winogrande (5-shot)              |72.61|
+|GSM8k (5-shot)                   |40.18|
+