Adding Evaluation Results (#1)

- Adding Evaluation Results (eefcab2ef284bd752ea5e73fd26171b6ee280759)


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

README.md

@@ -1,13 +1,107 @@
 ---
-base_model:
-- shuttleai/shuttle-2.5-mini
-- mistralai/Mistral-Nemo-Base-2407
-- Undi95/LocalC-12B-e2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- shuttleai/shuttle-2.5-mini
+- mistralai/Mistral-Nemo-Base-2407
+- Undi95/LocalC-12B-e2.0
+model-index:
+- name: StableProse
+  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: 19.72
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nlpguy/StableProse
+      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: 30.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nlpguy/StableProse
+      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: 4.68
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nlpguy/StableProse
+      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: 7.05
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nlpguy/StableProse
+      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: 8.87
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nlpguy/StableProse
+      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: 27.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nlpguy/StableProse
+      name: Open LLM Leaderboard
 ---
 
 **EDIT: Early IFEval Results aren't looking great, keep this in mind when using this model.**
@@ -44,3 +138,17 @@ slices:
   - layer_range: [0, 40]
     model: shuttleai/shuttle-2.5-mini
 ```
+
+# [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_nlpguy__StableProse)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |16.32|
+|IFEval (0-Shot)    |19.72|
+|BBH (3-Shot)       |30.18|
+|MATH Lvl 5 (4-Shot)| 4.68|
+|GPQA (0-shot)      | 7.05|
+|MuSR (0-shot)      | 8.87|
+|MMLU-PRO (5-shot)  |27.43|
+