Smaug 72B V0.1

🚀 Smaug-72B-v0.1

Smaug-72B-v0.1, a new open - source model, has topped the Open LLM Leaderboard by HuggingFace with an average score over 80%, powered by a novel fine - tuning technique.

🚀 Quick Start

Smaug-72B-v0.1 has arrived! It has achieved the first place on the Open LLM Leaderboard by HuggingFace, becoming the first open - source model to surpass an average score of 80%.

✨ Features

• Fine - tuning Base: Smaug-72B is directly finetuned from moreh/MoMo-72B-lora-1.8.7-DPO and ultimately based on Qwen-72B.
• New Fine - tuning Technique: It is created using a new fine - tuning technique, DPO - Positive (DPOP), and new pairwise preference versions of ARC, HellaSwag, and MetaMath, along with other existing datasets. The technique and full training details are introduced in the paper: https://arxiv.org/abs/2402.13228.
• Innovative Loss Function: DPOP is designed to avoid the failure mode of the standard DPO loss, especially in datasets with low edit distances between pairs of completions. It outperforms DPO across a wide variety of datasets and downstream tasks.

📚 Documentation

Evaluation Results

MT - Bench

We ran MT - Bench with the llama - 2 conversation template and the system prompt set to the Qwen system prompt. The results in single model mode are as follows:

Contamination Results

We generate our contamination numbers using https://github.com/swj0419/detect-pretrain-code-contamination/tree/master, with Llama7B as our reference model.

• Smaug-72B Results: | ARC | TruthfulQA | GSM8K | | --- | --- | --- | | 0.20| 0.45| 1.00|
• MoMo-72B-lora-1.8.7-DPO Results: | ARC | TruthfulQA | GSM8K | | --- | --- | --- | | 0.20| 0.39| 1.00|
• Llama - 2 - 70B Results: | ARC | TruthfulQA | GSM8K | | --- | --- | --- | | 0.22| 0.51| 0.89|

Sample MT Bench results

Example 1

Question Imagine you are writing a blog post comparing two popular smartphone models. Develop an outline for the blog post, including key points and subheadings to effectively compare and contrast the features, performance, and user experience of the two models. Please answer in fewer than 200 words.

Response Outline:

1. Introduction to the two smartphone models being compared (mention brand names and models)
2. Design and Build Quality
   • Comparison of dimensions, weight, materials used, and overall aesthetic appeal
   • Water and dust resistance, if applicable
3. Display and Screen Quality
   • Comparison of screen technology (OLED, IPS LCD, etc.)
   • Display resolution, refresh rate, and brightness levels
4. Performance and Hardware
   • Processor, RAM, and storage configurations
   • Comparison of benchmark scores (e.g., AnTuTu, Geekbench)
5. Camera System and Image Quality
   • Comparison of primary, ultra - wide, telephoto, and macro lenses (if available)
   • Comparison of low - light performance and image processing capabilities
6. Battery Life and Charging
   • Battery capacity and estimated usage time
   • Charging technologies (wired, wireless, fast charging, reverse charging)
7. Software and User Experience
   • Comparison of operating systems (iOS vs. Android) and their features
   • User interface, customization options, and app ecosystem
8. Additional Features and Extras
   • Comparison of biometric authentication (fingerprint, face unlock, etc.)
   • Additional features like NFC, 5G connectivity, and audio quality
9. Pricing and Value for Money
   • Comparison of retail prices and current offers
   • Assessment of overall value considering the features and performance
10. Conclusion and recommendation for potential buyers based on their preferences

Example 2

Question In a survey conducted at a local high school, preferences for a new school color were measured: 58% of students liked the color blue, 45% preferred green, and 22% liked both colors. If we randomly pick a student from the school, what's the probability that they would like neither blue nor green?

Answer To find the probability that a randomly picked student would like neither blue nor green, we need to find the percentage of students who like only one color or neither color. From the given information, we know:

• 58% like blue
• 45% prefer green
• 22% like both colors To find the percentage of students who like only one color, we can subtract the percentage of students who like both colors from the sum of students who like blue and green:
• 58% (blue)+ 45% (green)- 22% (both)= 83% Now, to find the probability of a student liking neither blue nor green, we subtract the percentage of students who like at least one color from 100%:
• 100% - 83% = 17% So, the probability that a randomly picked student would like neither blue nor green is 17%.

Example 3

Question Implement a program to find the common elements in two arrays without using any extra data structures.

Answer

def find_common_elements(arr1, arr2):
    common_elements = []
    for num1 in arr1:
        if num1 in arr2 and num1 not in common_elements:
            common_elements.append(num1)
    return common_elements

# Example usage:
array1 = [1, 2, 3, 4, 5]
array2 = [4, 5, 6, 7, 8]
print(find_common_elements(array1, array2))  # Output: [4, 5]

Example 4

Question Identify the named entities (people, organizations, locations) mentioned in the given news article. Please generate a JSON dictionary that lists the named entities in three separate groups based on their entity types. The key is the type of entity and the value is a list of strings. Yesterday, Adamson Emerson, the CEO of Faraday, and Dieter Zetsche, the CEO of Daimler AG, announced plans to build a new Gigafactory in Berlin. The facility will be a joint venture between Faraday and Daimler, producing electric vehicles and battery packs for both companies, creating thousands of job opportunities in the region. Emerson and Zetsche stated that the strategic location of Berlin, coupled with its skilled workforce and strong infrastructure, makes it an ideal choice for expansion. The new Gigafactory aims to meet the growing demand for electric vehicles in Europe and contribute to a sustainable future. Volkswagen CEO Herbert Diess welcomed the news, saying greater collaboration will, benefit the auto industry's transition to e - mobility.

Answer

{
  "people": ["Adamson Emerson", "Dieter Zetsche", "Herbert Diess"],
  "organizations": ["Faraday", "Daimler AG", "Volkswagen"],
  "locations": ["Berlin", "Europe"]
}

Citation

Please cite the paper if you use data, model, or method in this repo.

@article{pal2024smaug,
  title={Smaug: Fixing Failure Modes of Preference Optimisation with DPO - Positive},
  author={Pal, Arka and Karkhanis, Deep and Dooley, Samuel and Roberts, Manley and Naidu, Siddartha and White, Colin},
  journal={arXiv preprint arXiv:2402.13228},
  year={2024}
}

📄 License

This project is under the Tongyi Qianwen License Agreement.