Adding Evaluation Results (#1)

- Adding Evaluation Results (d06ea9af36a285d92e5198d5c522305b7c192cfa)


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

README.md

@@ -1,9 +1,104 @@
 ---
-license: llama3
 language:
 - en
+license: llama3
 library_name: transformers
 pipeline_tag: text2text-generation
+model-index:
+- name: orca_mini_v6_8b_dpo
+  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: 38.83
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pankajmathur/orca_mini_v6_8b_dpo
+      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: 32.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pankajmathur/orca_mini_v6_8b_dpo
+      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: 5.51
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pankajmathur/orca_mini_v6_8b_dpo
+      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: 6.82
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pankajmathur/orca_mini_v6_8b_dpo
+      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: 9.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pankajmathur/orca_mini_v6_8b_dpo
+      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: 28.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pankajmathur/orca_mini_v6_8b_dpo
+      name: Open LLM Leaderboard
 ---
 
 **Model Name: Llama 3 orca_mini_v6_8b_dpo**
@@ -67,3 +162,17 @@ GGUF : Coming Soon
 
 AWQ: Coming Soon
 
+
+# [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_pankajmathur__orca_mini_v6_8b_dpo)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.29|
+|IFEval (0-Shot)    |38.83|
+|BBH (3-Shot)       |32.48|
+|MATH Lvl 5 (4-Shot)| 5.51|
+|GPQA (0-shot)      | 6.82|
+|MuSR (0-shot)      | 9.26|
+|MMLU-PRO (5-shot)  |28.85|
+