Adding Evaluation Results

README.md

@@ -1,13 +1,116 @@
 ---
+language:
+- en
+license: cc-by-4.0
 library_name: transformers
 tags:
 - llm
 - 7b
-license: cc-by-4.0
-language:
-- en
 datasets:
 - argilla/distilabel-math-preference-dpo
+model-index:
+- name: jaskier-7b-dpo-v5.6
+  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: 73.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v5.6
+      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: 89.0
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v5.6
+      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: 64.38
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v5.6
+      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: 77.81
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v5.6
+      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: 84.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v5.6
+      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: 69.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v5.6
+      name: Open LLM Leaderboard
 ---
 
 # Jaskier-7b-dpo-v5.6
@@ -51,4 +154,17 @@ If you still find any issues with "INST" character chain appearing in generated
 
 At bards.ai, we focus on providing machine learning expertise and skills to our partners, particularly in the areas of nlp, machine vision and time series analysis. Our team is located in Wroclaw, Poland. Please visit our website for more information: bards.ai
 
-Let us know if you use our model :). Also, if you need any help, feel free to contact us at info@bards.ai
+Let us know if you use our model :). Also, if you need any help, feel free to contact us at info@bards.ai
+# [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_bardsai__jaskier-7b-dpo-v5.6)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |76.41|
+|AI2 Reasoning Challenge (25-Shot)|73.04|
+|HellaSwag (10-Shot)              |89.00|
+|MMLU (5-Shot)                    |64.38|
+|TruthfulQA (0-shot)              |77.81|
+|Winogrande (5-shot)              |84.53|
+|GSM8k (5-shot)                   |69.67|
+