Adding Evaluation Results

README.md

@@ -1,5 +1,100 @@
 ---
 license: apache-2.0
+model-index:
+- name: Homer-v1.0-Qwen2.5-72B
+  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: 76.28
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=newsbang/Homer-v1.0-Qwen2.5-72B
+      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: 62.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=newsbang/Homer-v1.0-Qwen2.5-72B
+      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: 48.34
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=newsbang/Homer-v1.0-Qwen2.5-72B
+      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: 22.15
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=newsbang/Homer-v1.0-Qwen2.5-72B
+      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: 17.9
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=newsbang/Homer-v1.0-Qwen2.5-72B
+      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: 57.17
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=newsbang/Homer-v1.0-Qwen2.5-72B
+      name: Open LLM Leaderboard
 ---
 
 Homer-v1.0-Qwen2.5-72B is a fine-tuned version of Qwen2.5-72B using a large amount of instruction-based data.  
@@ -37,4 +132,17 @@ generated_ids = [
 ]
 
 response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
-```
+```
+# [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/newsbang__Homer-v1.0-Qwen2.5-72B-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |47.35|
+|IFEval (0-Shot)    |76.28|
+|BBH (3-Shot)       |62.27|
+|MATH Lvl 5 (4-Shot)|48.34|
+|GPQA (0-shot)      |22.15|
+|MuSR (0-shot)      |17.90|
+|MMLU-PRO (5-shot)  |57.17|
+