Magpie-Align/Llama-3-8B-Magpie-Pro-SFT-300K-v0.1

Hugging Face
TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedLicense:llama3Architecture:Transformer0.0K Featherless Exclusive Warm

Magpie-Align/Llama-3-8B-Magpie-Pro-SFT-300K-v0.1 is an 8 billion parameter Llama-3-based language model developed by Magpie-Align, fine-tuned on 300K high-quality instruction instances generated by the Magpie self-synthesis method. This model achieves performance comparable to the official Llama-3-8B-Instruct model through supervised fine-tuning (SFT) alone, demonstrating strong capabilities on alignment benchmarks such as AlpacaEval and ArenaHard. It is particularly effective for tasks requiring robust instruction following and general conversational abilities.

Loading preview...

Model Overview

Magpie-Align/Llama-3-8B-Magpie-Pro-SFT-300K-v0.1 is an 8 billion parameter model based on Meta's Llama-3-8B architecture. It has been fine-tuned using the Magpie self-synthesis method, which generates high-quality instruction data by prompting aligned LLMs. This model leverages a filtered dataset of 300,000 such instances, enabling it to achieve strong performance with supervised fine-tuning (SFT) alone.

Key Capabilities & Differentiators

  • Self-Synthesized Alignment Data: Utilizes the innovative Magpie method to create a large-scale, high-quality alignment dataset, addressing the limitations of traditional human-labeled or limited-scope datasets.
  • Comparable to Llama-3-8B-Instruct: Achieves performance on par with the official Llama-3-8B-Instruct model, despite the latter's more extensive training with 10 million data points and feedback learning.
  • Strong Benchmark Performance: Demonstrates competitive results on alignment benchmarks:
    • Alpaca Eval 2 (GPT-4-Turbo-1106): 25.08 (LC), 29.47 (WR)
    • Alpaca Eval 2 (Llama-3-8B-Instruct): 52.12 (LC), 53.43 (WR)
    • Arena Hard: 18.9
  • Efficient Alignment: Shows that high-quality SFT data can surpass models trained with both SFT and preference optimization (like DPO with UltraFeedback) on certain alignment tasks.

Use Cases

This model is well-suited for applications requiring robust instruction following and general conversational AI, particularly where performance comparable to Llama-3-Instruct is desired with a focus on efficient SFT-based alignment. Developers can leverage its strong alignment capabilities for various downstream tasks.

Finetunes
2 models