Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
-license: apache-2.0
 language:
 - en
-datasets:
-- Intel/orca_dpo_pairs
-pipeline_tag: conversational
+license: apache-2.0
 library_name: peft
 tags:
 - llm
 - 7b
+datasets:
+- Intel/orca_dpo_pairs
+pipeline_tag: conversational
+model-index:
+- name: jaskier-7b-dpo-v2
+  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: 69.28
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v2
+      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: 86.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v2
+      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: 64.92
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v2
+      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=bardsai/jaskier-7b-dpo-v2
+      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: 80.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v2
+      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: 71.8
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v2
+      name: Open LLM Leaderboard
 ---
 # Jaskier 7b DPO V2
 
@@ -73,4 +176,17 @@ print(sequences[0])
 
 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 [email protected]
+Let us know if you use our model :). Also, if you need any help, feel free to contact us at [email protected]
+# [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-v2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |72.53|
+|AI2 Reasoning Challenge (25-Shot)|69.28|
+|HellaSwag (10-Shot)              |86.80|
+|MMLU (5-Shot)                    |64.92|
+|TruthfulQA (0-shot)              |61.64|
+|Winogrande (5-shot)              |80.74|
+|GSM8k (5-shot)                   |71.80|
+