Adding Evaluation Results (#1)

- Adding Evaluation Results (5aa86626e6964a756ab62b15a85e8d7924202a5b)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,12 +1,107 @@
 ---
-license: apache-2.0
-datasets:
-- allenai/tulu-3-sft-mixture
-- allenai/llama-3.1-tulu-3-8b-preference-mixture
 language:
 - en
+license: apache-2.0
 base_model:
 - HuggingFaceTB/SmolLM2-1.7B-Instruct
+datasets:
+- allenai/tulu-3-sft-mixture
+- allenai/llama-3.1-tulu-3-8b-preference-mixture
+model-index:
+- name: SmolLM2-MedIT-Upscale-2B
+  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: 64.29
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/SmolLM2-MedIT-Upscale-2B
+      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: 10.51
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/SmolLM2-MedIT-Upscale-2B
+      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: 1.06
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/SmolLM2-MedIT-Upscale-2B
+      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: 1.9
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/SmolLM2-MedIT-Upscale-2B
+      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: 2.45
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/SmolLM2-MedIT-Upscale-2B
+      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: 10.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/SmolLM2-MedIT-Upscale-2B
+      name: Open LLM Leaderboard
 ---
 # SmolLM2-MedIT-Upscale-2B
 
@@ -76,4 +171,17 @@ If you use this model in your research, please cite it as follows:
   publisher = {Hugging Face},
   url = {https://huggingface.co/meditsolutions/SmolLM2-MedIT-Upscale-2B},
 }
-```
+```
+# [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_meditsolutions__SmolLM2-MedIT-Upscale-2B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |15.17|
+|IFEval (0-Shot)    |64.29|
+|BBH (3-Shot)       |10.51|
+|MATH Lvl 5 (4-Shot)| 1.06|
+|GPQA (0-shot)      | 1.90|
+|MuSR (0-shot)      | 2.45|
+|MMLU-PRO (5-shot)  |10.78|
+