Adding Evaluation Results (#1)

- Adding Evaluation Results (1048eb3f21c1fd310d0bda5325b647637590da1b)


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

README.md

@@ -1,12 +1,107 @@
 ---
-base_model:
-- flammenai/Mahou-1.5-mistral-nemo-12B
-- nbeerbower/Mistral-Nemo-12B-abliterated-LORA
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: apache-2.0
+base_model:
+- flammenai/Mahou-1.5-mistral-nemo-12B
+- nbeerbower/Mistral-Nemo-12B-abliterated-LORA
+model-index:
+- name: Mahou-1.5-mistral-nemo-12B-lorablated
+  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: 68.25
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
+      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: 36.08
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
+      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: 5.29
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
+      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: 3.91
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
+      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: 16.55
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
+      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: 28.6
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
+      name: Open LLM Leaderboard
 ---
 # Mahou-1.5-mistral-nemo-12B-lorablated
 
@@ -39,4 +134,17 @@ slices:
     parameters:
       weight: 1.0
 
-```
+```
+# [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_nbeerbower__Mahou-1.5-mistral-nemo-12B-lorablated)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |26.45|
+|IFEval (0-Shot)    |68.25|
+|BBH (3-Shot)       |36.08|
+|MATH Lvl 5 (4-Shot)| 5.29|
+|GPQA (0-shot)      | 3.91|
+|MuSR (0-shot)      |16.55|
+|MMLU-PRO (5-shot)  |28.60|
+