Adding Evaluation Results (#1)

- Adding Evaluation Results (a5db2f75a7ab5f490638d090592936a823391946)


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

README.md

@@ -1,14 +1,109 @@
 ---
+license: other
+tags:
+- mergekit
+- merge
 base_model:
 - Qwen/Qwen2.5-3B
 - Qwen/Qwen2.5-3B-Instruct
 - arcee-ai/raspberry-3B
-license: other
 license_name: qwen-research
 license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE
-tags:
-  - mergekit
-  - merge
+model-index:
+- name: Rombos-LLM-V2.5.1-Qwen-3b
+  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: 25.95
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.5.1-Qwen-3b
+      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: 14.88
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.5.1-Qwen-3b
+      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: 8.31
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.5.1-Qwen-3b
+      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: 3.24
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.5.1-Qwen-3b
+      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: 7.82
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.5.1-Qwen-3b
+      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: 19.1
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.5.1-Qwen-3b
+      name: Open LLM Leaderboard
 ---
 # Rombos-LLM-V2.5.1-Qwen-3b 
 
@@ -37,4 +132,17 @@ parameters:
   normalize: true
   int8_mask: true
 dtype: bfloat16
-```
+```
+# [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_rombodawg__Rombos-LLM-V2.5.1-Qwen-3b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |13.22|
+|IFEval (0-Shot)    |25.95|
+|BBH (3-Shot)       |14.88|
+|MATH Lvl 5 (4-Shot)| 8.31|
+|GPQA (0-shot)      | 3.24|
+|MuSR (0-shot)      | 7.82|
+|MMLU-PRO (5-shot)  |19.10|
+