Adding Evaluation Results (#2)

- Adding Evaluation Results (e4650f396aa379e5e644bcd1c965684e29c43336)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,12 +1,115 @@
 ---
-base_model:
-- Nitral-AI/Lelemon-Maid-7B
-- Nitral-AI/KukulStanta-7B
+license: other
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: other
+base_model:
+- Nitral-AI/Lelemon-Maid-7B
+- Nitral-AI/KukulStanta-7B
+model-index:
+- name: Stanta-Lelemon-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: 67.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Nitral-AI/Stanta-Lelemon-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: 86.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Nitral-AI/Stanta-Lelemon-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: 64.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Nitral-AI/Stanta-Lelemon-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: 59.58
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Nitral-AI/Stanta-Lelemon-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: 79.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Nitral-AI/Stanta-Lelemon-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: 61.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Nitral-AI/Stanta-Lelemon-Maid-7B
+      name: Open LLM Leaderboard
 ---
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/pQ5xEj4JOyNF_dvBkuIa6.png)
@@ -21,4 +124,17 @@ To use the multimodal capabilities of this model and use **vision** you need to
  
  * You can load the **mmproj** by using the corresponding section in the interface:
 
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/UX6Ubss2EPNAT3SKGMLe0.png)
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/UX6Ubss2EPNAT3SKGMLe0.png)
+# [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_Nitral-AI__Stanta-Lelemon-Maid-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.79|
+|AI2 Reasoning Challenge (25-Shot)|67.58|
+|HellaSwag (10-Shot)              |86.03|
+|MMLU (5-Shot)                    |64.79|
+|TruthfulQA (0-shot)              |59.58|
+|Winogrande (5-shot)              |79.64|
+|GSM8k (5-shot)                   |61.11|
+