Adding Evaluation Results

README.md

@@ -1,16 +1,111 @@
 ---
+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: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 54.47
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beowolx/CodeNinja-1.0-OpenChat-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 21.71
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beowolx/CodeNinja-1.0-OpenChat-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 5.21
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beowolx/CodeNinja-1.0-OpenChat-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 5.93
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beowolx/CodeNinja-1.0-OpenChat-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 11.54
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beowolx/CodeNinja-1.0-OpenChat-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 22.39
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beowolx/CodeNinja-1.0-OpenChat-7B
+      name: Open LLM Leaderboard
 ---
 
 <p align="center">
@@ -92,4 +187,17 @@ 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/open-llm-leaderboard/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.               |20.21|
+|IFEval (0-Shot)    |54.47|
+|BBH (3-Shot)       |21.71|
+|MATH Lvl 5 (4-Shot)| 5.21|
+|GPQA (0-shot)      | 5.93|
+|MuSR (0-shot)      |11.54|
+|MMLU-PRO (5-shot)  |22.39|
+