README.md

metadata

title: README
emoji: 🐦
colorFrom: pink
colorTo: indigo
sdk: static
pinned: false

Hi, I am a magpie 🐦!

🕸️ Project Website: https://magpie-align.github.io/

📄 Technical Report: https://arxiv.org/abs/2406.08464

🤗 HF Paper Page: https://huggingface.co/papers/2406.08464

😬 Codes: https://github.com/magpie-align/magpie

🤗 Magpie Demo: https://huggingface.co/spaces/davanstrien/magpie (Thanks a lot for the implementation from @davanstrien!)

🐦 Chat with Magpie: https://huggingface.co/spaces/flydust/Chat-with-Magpie

Questions? Please contact Zhangchen by email or raise an issue in Github.

Dataset Navigation 🧭

Meta Llama 3

Model Name	Dataset	Type	Description
Llama 3 70B Instruct	Magpie-Pro-1M	SFT	1M Raw conversations built with Meta Llama 3 70B.
Llama 3 70B Instruct	Magpie-Pro-300K-Filtered	SFT	Apply a filter and select 300K high quality conversations.
Llama 3 70B Instruct	Magpie-Pro-MT-300K	SFT	Select 300K difficult questions and extend to multi-turn conversations.
Llama 3 70B Instruct	Magpie-Pro-DPO-100K	DPO	DPO dataset via Best-of-N sampling and rewards.
Llama 3 8B Instruct	Magpie-Air-3M	SFT	3M Raw conversations built with Meta Llama 3 8B.
Llama 3 8B Instruct	Magpie-Air-300K-Filtered	SFT	Apply a filter and select 300K high quality data.
Llama 3 8B Instruct	Magpie-Air-MT-300K	SFT	Select 300K difficult questions and extend to multi-turn conversations.
Llama 3 8B Instruct	Magpie-Air-DPO-100K	DPO	DPO dataset via Best-of-N sampling and rewards.

Meta Llama 3.1

Model Name	Dataset	Type	Description
Llama 3.1 70B Instruct	Magpie-Llama-3.1-Pro-1M	SFT	1M Raw conversations built with Meta Llama 3.1 70B.
Llama 3.1 70B Instruct	Magpie-Llama-3.1-Pro-300K-Filtered	SFT	Apply a filter and select 300K high quality conversations.
Llama 3.1 70B Instruct	Magpie-Llama-3.1-Pro-500K-Filtered	SFT	Apply a filter and select 500K high quality conversations.
Llama 3.1 70B Instruct	Magpie-Llama-3.1-Pro-MT-500K	SFT	Select 500K difficult questions and extend to multi-turn conversations.
Llama 3.1 70B Instruct	Magpie-Llama-3.1-Pro-DPO-100K	SFT	DPO dataset via Best-of-N sampling and rewards.

Qwen2

Model Name	Dataset	Type	Description
Qwen2 72B Instruct	Magpie-Qwen2-Pro-1M	SFT	1M Raw conversations built with Qwen2 72B Instruct.
Qwen2 72B Instruct	Magpie-Qwen2-Pro-300K-Filtered	SFT	Apply a filter and select 300K high quality conversations.
Qwen2 72B Instruct	Magpie-Qwen2-Pro-200K-Chinese	SFT	Apply a filter and select 200K high quality Chinese conversations.
Qwen2 72B Instruct	Magpie-Qwen2-Pro-200K-English	SFT	Apply a filter and select 200K high quality English conversations.
Qwen2 7B Instruct	Magpie-Qwen2-Air-3M	SFT	3M Raw conversations built with Qwen2 7B Instruct.
Qwen2 7B Instruct	Magpie-Qwen2-Air-300K-Filtered	SFT	Apply a filter and select 300K high quality conversations.

Phi-3

Model Name	Dataset	Type	Description
Phi-3 Medium Instruct	Magpie-Phi3-Pro-1M	SFT	1M Raw conversations built with Phi-3 Medium Instruct.
Phi-3 Medium Instruct	Magpie-Phi3-Pro-300K-Filtered	SFT	Apply a filter and select 300K high quality conversations.

Gemma-2

Model Name	Dataset	Type	Description
Gemma-2-27b-it	Magpie-Gemma2-Pro-534K	SFT	534K conversations built with Gemma-2-27b-it.
Gemma-2-27b-it	Magpie-Gemma2-Pro-200K-Filtered	SFT	Apply a filter and select 200K conversations.