Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
-license: cc-by-4.0
 language:
 - en
+license: cc-by-4.0
 tags:
 - merge
 - not-for-all-audiences
 - nsfw
+model-index:
+- name: Silicon-Maid-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: 68.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SanjiWatsuki/Silicon-Maid-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: 86.52
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SanjiWatsuki/Silicon-Maid-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: 64.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SanjiWatsuki/Silicon-Maid-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: 61.64
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SanjiWatsuki/Silicon-Maid-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: 79.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SanjiWatsuki/Silicon-Maid-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: 61.94
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SanjiWatsuki/Silicon-Maid-7B
+      name: Open LLM Leaderboard
 ---
 
 <div style="display: flex; justify-content: center; align-items: center">
@@ -116,3 +219,17 @@ Below is an instruction that describes a task. Write a response that appropriate
 | [openchat/openchat_3.5](https://huggingface.co/openchat/openchat_3.5) [📄](https://gist.github.com/mlabonne/e23d7d8418619cf5b1ca10da391ac629) | 51.34 | 42.67 | 72.92 | 47.27 | 42.51 |
 | [berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) [📄](https://gist.github.com/mlabonne/c31cc46169ef3004c0df250017d5cac9) | 51.16 | 42.06 | 72.72 | 47.33 | 42.53 |
 | [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) [📄](https://gist.github.com/mlabonne/32a36f448fd36a3100c325d51d01c0a1) | 50.99 | 37.33 | 71.83 | 55.1 | 39.7 |
+
+# [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_SanjiWatsuki__Silicon-Maid-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.31|
+|AI2 Reasoning Challenge (25-Shot)|68.17|
+|HellaSwag (10-Shot)              |86.52|
+|MMLU (5-Shot)                    |64.58|
+|TruthfulQA (0-shot)              |61.64|
+|Winogrande (5-shot)              |79.01|
+|GSM8k (5-shot)                   |61.94|
+