Adding Evaluation Results (#1)

- Adding Evaluation Results (81b02e5c21eef2488ba7dd0a39ca45883415ad73)


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

README.md

@@ -1,14 +1,109 @@
 ---
-base_model: unsloth/qwen2.5-14b-bnb-4bit
+language:
+- en
+license: apache-2.0
 tags:
 - text-generation-inference
 - transformers
 - unsloth
 - qwen2
 - trl
-license: apache-2.0
-language:
-- en
+base_model: unsloth/qwen2.5-14b-bnb-4bit
+model-index:
+- name: Qwen2.5-Math-14B-Instruct-Alpha
+  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: 59.81
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Math-14B-Instruct-Alpha
+      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: 47.75
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Math-14B-Instruct-Alpha
+      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: 23.11
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Math-14B-Instruct-Alpha
+      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: 16.0
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Math-14B-Instruct-Alpha
+      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: 17.95
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Math-14B-Instruct-Alpha
+      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: 48.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Math-14B-Instruct-Alpha
+      name: Open LLM Leaderboard
 ---
 
 # Uploaded  model
@@ -41,3 +136,17 @@ This model is Qwen 2.5 14B fine tuned for a full epoch on the high quality [gara
 <img src="https://raw.githubusercontent.com/qingy1337/Storage/refs/heads/main/loss.svg" height="500"/>
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+# [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_qingy2019__Qwen2.5-Math-14B-Instruct-Alpha)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |35.46|
+|IFEval (0-Shot)    |59.81|
+|BBH (3-Shot)       |47.75|
+|MATH Lvl 5 (4-Shot)|23.11|
+|GPQA (0-shot)      |16.00|
+|MuSR (0-shot)      |17.95|
+|MMLU-PRO (5-shot)  |48.12|
+