Adding Evaluation Results (#3)

- Adding Evaluation Results (ef13c29d93dce26ecd5861bfa664d122dd114402)


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

README.md

@@ -1,7 +1,19 @@
 ---
+language:
+- en
 license: llama3.2
+library_name: transformers
 base_model:
 - meta-llama/Llama-3.2-1B-Instruct
+datasets:
+- argilla/OpenHermesPreferences
+- argilla/magpie-ultra-v0.1
+- argilla/Capybara-Preferences-Filtered
+- mlabonne/open-perfectblend
+- HuggingFaceTB/everyday-conversations-llama3.1-2k
+- WizardLMTeam/WizardLM_evol_instruct_V2_196k
+- ProlificAI/social-reasoning-rlhf
+pipeline_tag: text-generation
 model-index:
 - name: Llama-3.2-SUN-2.4B-v1.0.0
   results:
@@ -17,9 +29,11 @@ model-index:
     - type: inst_level_strict_acc and prompt_level_strict_acc
       value: 56.37
       name: strict accuracy
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 55.37
+      name: strict accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.4B-v1.0.0
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.4B-v1.0.0
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -33,9 +47,11 @@ model-index:
     - type: acc_norm
       value: 7.21
       name: normalized accuracy
+    - type: acc_norm
+      value: 7.17
+      name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.4B-v1.0.0
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.4B-v1.0.0
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -49,9 +65,11 @@ model-index:
     - type: exact_match
       value: 4.83
       name: exact match
+    - type: exact_match
+      value: 1.28
+      name: exact match
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.4B-v1.0.0
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.4B-v1.0.0
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -65,9 +83,11 @@ model-index:
     - type: acc_norm
       value: 1.01
       name: acc_norm
+    - type: acc_norm
+      value: 0.45
+      name: acc_norm
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.4B-v1.0.0
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.4B-v1.0.0
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -81,9 +101,11 @@ model-index:
     - type: acc_norm
       value: 3.02
       name: acc_norm
+    - type: acc_norm
+      value: 0.13
+      name: acc_norm
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.4B-v1.0.0
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.4B-v1.0.0
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -99,22 +121,12 @@ model-index:
     - type: acc
       value: 6.03
       name: accuracy
+    - type: acc
+      value: 7.17
+      name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.4B-v1.0.0
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.4B-v1.0.0
       name: Open LLM Leaderboard
-datasets:
-- argilla/OpenHermesPreferences
-- argilla/magpie-ultra-v0.1
-- argilla/Capybara-Preferences-Filtered
-- mlabonne/open-perfectblend
-- HuggingFaceTB/everyday-conversations-llama3.1-2k
-- WizardLMTeam/WizardLM_evol_instruct_V2_196k
-- ProlificAI/social-reasoning-rlhf
-language:
-- en
-pipeline_tag: text-generation
-library_name: transformers
 ---
 
 # MedIT SUN 2.5B
@@ -165,4 +177,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |MATH Lvl 5 (4-Shot)| 4.83|
 |GPQA (0-shot)      | 1.01|
 |MuSR (0-shot)      | 3.02|
-|MMLU-PRO (5-shot)  | 6.03|
+|MMLU-PRO (5-shot)  | 6.03|
+# [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-3.2-SUN-2.5B-chat)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |11.93|
+|IFEval (0-Shot)    |55.37|
+|BBH (3-Shot)       | 7.17|
+|MATH Lvl 5 (4-Shot)| 1.28|
+|GPQA (0-shot)      | 0.45|
+|MuSR (0-shot)      | 0.13|
+|MMLU-PRO (5-shot)  | 7.17|
+