Zhangchen Xu's picture

Zhangchen Xu PRO

flydust

·

https://zhangchenxu.com/

AI & ML interests

LLM alignment; ML privacy, security and fairness

Recent Activity

liked a dataset about 6 hours ago

PrimeIntellect/NuminaMath-QwQ-CoT-5M

updated a dataset about 8 hours ago

Magpie-Align/Magpie-Reasoning-V1-150K

updated a dataset about 8 hours ago

Magpie-Align/Magpie-Reasoning-V1-150K-CoT-Skywork-O1-Llama-3.1-8B

View all activity

Organizations

flydust's activity

upvoted a collection 19 days ago

Magpie Reasoning Datasets

Reasoning datasets built by Magpie and its friends! • 8 items • Updated about 8 hours ago • 8

upvoted an article 19 days ago

Article

Fine-tune a SmolLM on domain-specific synthetic data from a LLM

By

•

25 days ago

• 32

upvoted a collection 24 days ago

Magpie-Llama3.3 Datasets

Dataset built with Meta Llama 3.3 70B. • 3 items • Updated 15 days ago • 1

upvoted a paper about 2 months ago

GRAPE: Generalizing Robot Policy via Preference Alignment

Paper • 2411.19309 • Published Nov 28, 2024 • 44

upvoted a paper 3 months ago

Stronger Models are NOT Stronger Teachers for Instruction Tuning

Paper • 2411.07133 • Published Nov 11, 2024 • 35

upvoted an article 3 months ago

Article

🇮🇹🇯🇵🇧🇷 Generating multilingual instruction datasets with Magpie 🐦‍⬛

By

•

Oct 21, 2024

• 18

upvoted a paper 4 months ago

Training Language Models to Self-Correct via Reinforcement Learning

Paper • 2409.12917 • Published Sep 19, 2024 • 136

upvoted 2 collections 5 months ago

MagpieLM

Aligning LMs with Fully Open Recipe + Synthetic Data Generated from Open-Source LMs. • 9 items • Updated 15 days ago • 16

Magpie Open Recipes

Open-aligned models using Magpie datasets. • 11 items • Updated 15 days ago • 1

upvoted 2 collections 6 months ago

Magpie-Llama3.1 Datasets

Dataset built with Meta Llama 3.1 70B. • 6 items • Updated 15 days ago • 3

Zebra Logic Bench

ZebraLogic Bench: Testing the Limits of LLMs in Logical Reasoning • 4 items • Updated 21 days ago • 5

upvoted a paper 7 months ago

ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates

Paper • 2406.12935 • Published Jun 17, 2024 • 1

upvoted 2 collections 7 months ago

synthetic-data-generation-demos

A collection of demos for various approaches to synthetic data generation • 4 items • Updated Jun 25, 2024 • 14

Magpie-Qwen2 Datasets

Dataset built with Qwen2 72B and Qwen2 7B. • 6 items • Updated 15 days ago • 10

upvoted an article 7 months ago

Article

Introducing Synthetic Data Workshop: Your Gateway to Easy Synthetic Dataset Creation

By

•

Jun 20, 2024

• 12

upvoted 3 collections 8 months ago

FP8 LLMs for vLLM

Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! • 44 items • Updated Oct 17, 2024 • 62

Magpie-Air Datasets (Llama-3)

Dataset built with Meta Llama 3 8B. • 6 items • Updated 15 days ago • 1

WildBench

4 items • Updated 21 days ago • 6

upvoted a paper 8 months ago

ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs

Paper • 2402.11753 • Published Feb 19, 2024 • 5

upvoted a collection 8 months ago

Magpie-Pro Datasets (Llama-3)

Dataset built with Meta Llama 3 70B. • 6 items • Updated 15 days ago • 16