Adding Evaluation Results (#1)

- Adding Evaluation Results (0e7934356ad64f2f81980cecf859bec5a0b314a5)


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

README.md

@@ -1,12 +1,115 @@
 ---
-base_model:
-- Test157t/Kunocchini-7b
-- Test157t/Pasta-Made_7b
+license: other
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: other
+base_model:
+- Test157t/Kunocchini-7b
+- Test157t/Pasta-Made_7b
+model-index:
+- name: Pasta-PrimaMaid-7b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 67.92
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-PrimaMaid-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 86.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-PrimaMaid-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 63.31
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-PrimaMaid-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 66.47
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-PrimaMaid-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 77.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-PrimaMaid-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 49.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-PrimaMaid-7b
+      name: Open LLM Leaderboard
 ---
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/kIbxbLm41WsJb86sjGgZw.jpeg)
 
@@ -38,4 +141,17 @@ parameters:
       value: [1, 0.5, 0.7, 0.3, 0]
     - value: 0.5
 dtype: bfloat16
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Test157t__Pasta-PrimaMaid-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.48|
+|AI2 Reasoning Challenge (25-Shot)|67.92|
+|HellaSwag (10-Shot)              |86.18|
+|MMLU (5-Shot)                    |63.31|
+|TruthfulQA (0-shot)              |66.47|
+|Winogrande (5-shot)              |77.90|
+|GSM8k (5-shot)                   |49.13|
+