Adding Evaluation Results

README.md

@@ -2,6 +2,101 @@
 license: apache-2.0
 base_model:
 - Qwen/Qwen2.5-14B
+model-index:
+- name: Virtuoso-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: 79.35
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=arcee-ai/Virtuoso-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: 50.4
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=arcee-ai/Virtuoso-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: 34.29
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=arcee-ai/Virtuoso-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: 11.52
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=arcee-ai/Virtuoso-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: 14.44
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=arcee-ai/Virtuoso-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: 46.57
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=arcee-ai/Virtuoso-Small
+      name: Open LLM Leaderboard
 ---
 
 <div align="center">
@@ -45,3 +140,17 @@ Virtuoso-Small is the debut public release of the Virtuoso series of models by A
 
 Virtuoso-Small is available under the Apache-2.0 license and can be deployed locally or accessed through an API at [models.arcee.ai](https://models.arcee.ai). For larger-scale or more demanding applications, consider Virtuoso-Forte or Virtuoso-Prime.
 
+
+# [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_arcee-ai__Virtuoso-Small)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |39.43|
+|IFEval (0-Shot)    |79.35|
+|BBH (3-Shot)       |50.40|
+|MATH Lvl 5 (4-Shot)|34.29|
+|GPQA (0-shot)      |11.52|
+|MuSR (0-shot)      |14.44|
+|MMLU-PRO (5-shot)  |46.57|
+