Adding Evaluation Results

README.md

@@ -1,21 +1,116 @@
 ---
-base_model:
-- MaziyarPanahi/calme-2.4-rys-78b
-datasets:
-- mlabonne/orpo-dpo-mix-40k
-library_name: transformers
-license: mit
 language:
 - en
-pipeline_tag: text-generation
+license: mit
+library_name: transformers
 tags:
 - orpo
 - qwen2
 - sft
 - chatml
+base_model:
+- MaziyarPanahi/calme-2.4-rys-78b
+datasets:
+- mlabonne/orpo-dpo-mix-40k
+pipeline_tag: text-generation
 inference: false
 model_creator: dfurman
 quantized_by: dfurman
+model-index:
+- name: CalmeRys-78B-Orpo-v0.1
+  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: 81.63
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/CalmeRys-78B-Orpo-v0.1
+      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: 61.92
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/CalmeRys-78B-Orpo-v0.1
+      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: 37.92
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/CalmeRys-78B-Orpo-v0.1
+      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: 20.02
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/CalmeRys-78B-Orpo-v0.1
+      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: 36.37
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/CalmeRys-78B-Orpo-v0.1
+      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: 66.8
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/CalmeRys-78B-Orpo-v0.1
+      name: Open LLM Leaderboard
 ---
 
 
@@ -186,3 +281,17 @@ Another variation is to use a spicy syrup. To make this, combine equal parts wat
 As always, adjust the quantity of jalapeño or the type of chili used to suit your taste. Enjoy responsibly!
 ```
 
+
+# [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_dfurman__CalmeRys-78B-Orpo-v0.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |50.78|
+|IFEval (0-Shot)    |81.63|
+|BBH (3-Shot)       |61.92|
+|MATH Lvl 5 (4-Shot)|37.92|
+|GPQA (0-shot)      |20.02|
+|MuSR (0-shot)      |36.37|
+|MMLU-PRO (5-shot)  |66.80|
+