Adding Evaluation Results (#2)

- Adding Evaluation Results (05acaa85c9d74dab5a2e7652387a7f601a66e348)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,15 +1,110 @@
 ---
-license: apache-2.0
 language:
 - en
-pipeline_tag: text-generation
+license: apache-2.0
+library_name: transformers
 tags:
 - role-play
 - fine-tuned
 - qwen2.5
 base_model:
 - Qwen/Qwen2.5-14B-Instruct
-library_name: transformers
+pipeline_tag: text-generation
+model-index:
+- name: oxy-1-small
+  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: 62.45
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=oxyapi/oxy-1-small
+      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: 41.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=oxyapi/oxy-1-small
+      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: 18.28
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=oxyapi/oxy-1-small
+      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: 16.22
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=oxyapi/oxy-1-small
+      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: 16.28
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=oxyapi/oxy-1-small
+      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: 44.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=oxyapi/oxy-1-small
+      name: Open LLM Leaderboard
 ---
 
 ![Oxy 1 Small](https://cdn-uploads.huggingface.co/production/uploads/64fb80c8bb362cbf2ff96c7e/tTIVIblPUbTYnlvHQQjXB.png)
@@ -87,4 +182,17 @@ If you find Oxy 1 Small useful in your research or applications, please cite it
   year={2024},
   howpublished={\url{https://huggingface.co/oxyapi/oxy-1-small}},
 }
-```
+```
+# [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_oxyapi__oxy-1-small)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |33.14|
+|IFEval (0-Shot)    |62.45|
+|BBH (3-Shot)       |41.18|
+|MATH Lvl 5 (4-Shot)|18.28|
+|GPQA (0-shot)      |16.22|
+|MuSR (0-shot)      |16.28|
+|MMLU-PRO (5-shot)  |44.45|
+