Adding Evaluation Results (#3)

- Adding Evaluation Results (794897da519d1ce7e72f2d829ac6d9425a778c8a)


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

README.md

@@ -1,15 +1,132 @@
 ---
-base_model:
-- mistralai/Mistral-7B-v0.1
+language:
+- en
+license: apache-2.0
+library_name: transformers
 tags:
 - qlora
 - dto
-language: 
-  - "en" 
-library_name: transformers
-license: "apache-2.0"
+base_model:
+- mistralai/Mistral-7B-v0.1
+model-index:
+- name: garten2-7b
+  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: 69.37
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/garten2-7b
+      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: 87.54
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/garten2-7b
+      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: 65.44
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/garten2-7b
+      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: 59.5
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/garten2-7b
+      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: 84.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/garten2-7b
+      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: 69.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/garten2-7b
+      name: Open LLM Leaderboard
 ---
 
 # Details
 
 Introducing Garten2-7B, a cutting-edge, small 7B all-purpose Language Model (LLM), designed to redefine the boundaries of artificial intelligence in natural language understanding and generation. Garten2-7B stands out with its unique architecture, expertly crafted to deliver exceptional performance in a wide array of tasks, from conversation to content creation.
+
+# [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_senseable__garten2-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |72.65|
+|AI2 Reasoning Challenge (25-Shot)|69.37|
+|HellaSwag (10-Shot)              |87.54|
+|MMLU (5-Shot)                    |65.44|
+|TruthfulQA (0-shot)              |59.50|
+|Winogrande (5-shot)              |84.69|
+|GSM8k (5-shot)                   |69.37|
+