Adding Evaluation Results (#3)

- Adding Evaluation Results (8c8c91e876da37636bdb152d1338bfe78b6fab5d)

README.md

@@ -1,10 +1,105 @@
 ---
-library_name: transformers
 license: apache-2.0
-datasets:
-- databricks/databricks-dolly-15k
+library_name: transformers
 base_model:
 - Qwen/Qwen2.5-0.5B-Instruct
+datasets:
+- databricks/databricks-dolly-15k
+model-index:
+- name: ECE-PRYMMAL0.5-FT
+  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: 18.51
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Youlln/ECE-PRYMMAL0.5-FT
+      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: 5.15
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Youlln/ECE-PRYMMAL0.5-FT
+      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: 0.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Youlln/ECE-PRYMMAL0.5-FT
+      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: 0.78
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Youlln/ECE-PRYMMAL0.5-FT
+      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: 1.43
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Youlln/ECE-PRYMMAL0.5-FT
+      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: 5.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Youlln/ECE-PRYMMAL0.5-FT
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -30,3 +125,17 @@ base_model:
 - **Dataset Used:** "databricks/databricks-dolly-15k"
 
 
+
+# [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_Youlln__ECE-PRYMMAL0.5-FT)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 5.20|
+|IFEval (0-Shot)    |18.51|
+|BBH (3-Shot)       | 5.15|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      | 0.78|
+|MuSR (0-shot)      | 1.43|
+|MMLU-PRO (5-shot)  | 5.30|
+