Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
+language:
+- en
 license: mit
+library_name: adapter-transformers
 datasets:
 - argilla/distilabel-intel-orca-dpo-pairs
 - jondurbin/truthy-dpo-v0.1
 - argilla/distilabel-math-preference-dpo
 - argilla/distilabel-capybara-dpo-7k-binarized
-language:
-- en
-library_name: adapter-transformers
 base_model: Technoculture/MT7Bi-sft
+model-index:
+- name: MedMerge-6-7b-alpha-dpo
+  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: 54.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/MedMerge-6-7b-alpha-dpo
+      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: 75.6
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/MedMerge-6-7b-alpha-dpo
+      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: 52.65
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/MedMerge-6-7b-alpha-dpo
+      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: 43.94
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/MedMerge-6-7b-alpha-dpo
+      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: 71.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/MedMerge-6-7b-alpha-dpo
+      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: 26.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/MedMerge-6-7b-alpha-dpo
+      name: Open LLM Leaderboard
 ---
 
 # Technoculture/MedMerge-6-7b-alpha-dpo
@@ -51,4 +154,17 @@ Total Size: 11.38k
 ### For full details of this dpo-training please read our notebook. 
 <a target="_blank" href="https://colab.research.google.com/github/dkshjn/Technoculture/blob/main/MedMerge_6_7b_alpha_dpo.ipynb">
   <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
-</a>
+</a>
+# [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_Technoculture__MedMerge-6-7b-alpha-dpo)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |53.94|
+|AI2 Reasoning Challenge (25-Shot)|54.27|
+|HellaSwag (10-Shot)              |75.60|
+|MMLU (5-Shot)                    |52.65|
+|TruthfulQA (0-shot)              |43.94|
+|Winogrande (5-shot)              |71.03|
+|GSM8k (5-shot)                   |26.16|
+