Adding Evaluation Results

README.md

@@ -1,16 +1,119 @@
 ---
+language:
+- en
 license: mit
+tags:
+- code
+- text-generation-inference
 datasets:
 - glaiveai/glaive-code-assistant-v2
 - TokenBender/code_instructions_122k_alpaca_style
-language:
-- en
 metrics:
 - code_eval
 pipeline_tag: text-generation
-tags:
-- code
-- text-generation-inference
+model-index:
+- name: CodeNinja-1.0-OpenChat-7B
+  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: 63.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beowolx/CodeNinja-1.0-OpenChat-7B
+      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: 83.65
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beowolx/CodeNinja-1.0-OpenChat-7B
+      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: 63.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beowolx/CodeNinja-1.0-OpenChat-7B
+      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: 47.16
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beowolx/CodeNinja-1.0-OpenChat-7B
+      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: 79.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beowolx/CodeNinja-1.0-OpenChat-7B
+      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: 66.57
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beowolx/CodeNinja-1.0-OpenChat-7B
+      name: Open LLM Leaderboard
 ---
 
 <p align="center">
@@ -92,4 +195,17 @@ def generate_one_completion(prompt: str):
 CodeNinja is licensed under the MIT License, with model usage subject to the Model License.
 
 ## Contact
-For queries or support, please open an issue in the repository.
+For queries or support, please open an issue in the repository.
+# [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_beowolx__CodeNinja-1.0-OpenChat-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.40|
+|AI2 Reasoning Challenge (25-Shot)|63.48|
+|HellaSwag (10-Shot)              |83.65|
+|MMLU (5-Shot)                    |63.77|
+|TruthfulQA (0-shot)              |47.16|
+|Winogrande (5-shot)              |79.79|
+|GSM8k (5-shot)                   |66.57|
+