Adding Evaluation Results

README.md

@@ -1,13 +1,108 @@
 ---
+license: other
 library_name: transformers
-datasets:
-- BAAI/Infinity-Instruct
 base_model:
 - Qwen/Qwen2.5-3B
-license: other
+datasets:
+- BAAI/Infinity-Instruct
 license_name: qwen-research
 license_link: https://huggingface.co/Qwen/Qwen2.5-3B/blob/main/LICENSE
 pipeline_tag: text-generation
+model-index:
+- name: Qwen2.5-3B-Infinity-Instruct-0625
+  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: 35.58
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jlzhou/Qwen2.5-3B-Infinity-Instruct-0625
+      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: 26.91
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jlzhou/Qwen2.5-3B-Infinity-Instruct-0625
+      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: 2.04
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jlzhou/Qwen2.5-3B-Infinity-Instruct-0625
+      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: 2.57
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jlzhou/Qwen2.5-3B-Infinity-Instruct-0625
+      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: 8.13
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jlzhou/Qwen2.5-3B-Infinity-Instruct-0625
+      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: 24.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jlzhou/Qwen2.5-3B-Infinity-Instruct-0625
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -86,3 +181,17 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
 
 [More Information Needed]
+
+# [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/jlzhou__Qwen2.5-3B-Infinity-Instruct-0625-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |16.61|
+|IFEval (0-Shot)    |35.58|
+|BBH (3-Shot)       |26.91|
+|MATH Lvl 5 (4-Shot)| 2.04|
+|GPQA (0-shot)      | 2.57|
+|MuSR (0-shot)      | 8.13|
+|MMLU-PRO (5-shot)  |24.43|
+