Adding Evaluation Results (#2)

- Adding Evaluation Results (9d3a1e26c7d7b76d93ac47ab326e951191d17029)


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

README.md

@@ -1,16 +1,119 @@
 ---
+language:
+- en
+license: openrail
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - SanjiWatsuki/Sonya-7B
 - EmbeddedLLM/Mistral-7B-Merge-14-v0.1
 - SanjiWatsuki/Kunoichi-7B
-tags:
-- mergekit
-- merge
-license: openrail
-language:
-- en
-library_name: transformers
 pipeline_tag: text-generation
+model-index:
+- name: Mistral_Sonyichi-7B-slerp
+  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: 67.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
+      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: 86.43
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
+      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: 63.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
+      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: 63.25
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
+      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: 78.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
+      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: 63.84
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
+      name: Open LLM Leaderboard
 ---
 # merged
 ![intro](332f1afc-d0b6-47f8-8a1c-b4bdccea94b4.png "Intro")
@@ -49,4 +152,17 @@ slices:
     model: SanjiWatsuki/Sonya-7B
   - layer_range: [0, 32]
     model: SanjiWatsuki/Kunoichi-7B
-```
+```
+# [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_s3nh__Mistral_Sonyichi-7B-slerp)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.52|
+|AI2 Reasoning Challenge (25-Shot)|67.49|
+|HellaSwag (10-Shot)              |86.43|
+|MMLU (5-Shot)                    |63.58|
+|TruthfulQA (0-shot)              |63.25|
+|Winogrande (5-shot)              |78.53|
+|GSM8k (5-shot)                   |63.84|
+