Adding Evaluation Results (#1)

- Adding Evaluation Results (ed2a8f72eaa16f56cfb3d46607f5d71f6a37f30d)


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

README.md

@@ -1,13 +1,108 @@
 ---
-license: llama3.1
 language:
 - en
+license: llama3.1
+tags:
+- medit-mesh
 base_model:
 - meta-llama/Llama-3.1-8B-Instruct
 - arcee-ai/Llama-3.1-SuperNova-Lite
 pipeline_tag: text-generation
-tags:
-- medit-mesh
+model-index:
+- name: Llama-3.1-MedIT-SUN-8B
+  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: 78.37
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.1-MedIT-SUN-8B
+      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: 32.0
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.1-MedIT-SUN-8B
+      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: 20.02
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.1-MedIT-SUN-8B
+      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: 7.83
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.1-MedIT-SUN-8B
+      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: 9.64
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.1-MedIT-SUN-8B
+      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: 32.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.1-MedIT-SUN-8B
+      name: Open LLM Leaderboard
 ---
 
 # Llama-3.1-MedIT-SUN-8B
@@ -35,4 +130,17 @@ This model was developed primarily for testing and research purposes, exploring
 
 ## Usage Notes
 
-As this is a test model, it is recommended for research and experimental purposes only. Users should be aware of its experimental nature when considering it for any applications.
+As this is a test model, it is recommended for research and experimental purposes only. Users should be aware of its experimental nature when considering it for any applications.
+# [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__Llama-3.1-MedIT-SUN-8B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |30.04|
+|IFEval (0-Shot)    |78.37|
+|BBH (3-Shot)       |32.00|
+|MATH Lvl 5 (4-Shot)|20.02|
+|GPQA (0-shot)      | 7.83|
+|MuSR (0-shot)      | 9.64|
+|MMLU-PRO (5-shot)  |32.40|
+