8 7 7

WeihaoZeng

AndrewZeng

https://github.com/Zeng-WH

AI & ML interests

None yet

Recent Activity

updated a dataset about 2 months ago

AndrewZeng/math_scaling

View all activity

Organizations

AndrewZeng's activity

updated a dataset about 2 months ago

AndrewZeng/math_scaling

Viewer • Updated Oct 7 • 100 • 11

upvoted a paper 4 months ago

FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue

Paper • 2306.10315 • Published Jun 17, 2023 • 1

authored 5 papers 4 months ago

What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning

Paper • 2312.15685 • Published Dec 25, 2023 • 16

DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning

Paper • 2402.09136 • Published Feb 14 • 1

CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery

Paper • 2406.08587 • Published Jun 12 • 15

Aqulia-Med LLM: Pioneering Full-Process Open-Source Medical Language Models

Paper • 2406.12182 • Published Jun 18

Automatic Instruction Evolving for Large Language Models

Paper • 2406.00770 • Published Jun 2 • 1

upvoted a paper 4 months ago

Automatic Instruction Evolving for Large Language Models

Paper • 2406.00770 • Published Jun 2 • 1

Reacted to WizardLM's post with 👍🚀 4 months ago

Post

9596

🔥 🔥🔥
Excited to announce WizardLM new Paper: Auto Evol-Instruct!

🐦 Twitter: https://x.com/WizardLM_AI/status/1812857977122202087

📃 Paper: https://arxiv.org/pdf/2406.00770

🤖 1. Fully AI-Powered Pipeline

Auto Evol-Instruct automatically involves an iterative process of optimizing an Evol-Instruct V1 into an optimal one. The pipeline consists of two critical stages: Evol Trajectory Analysis, where the optimizer LLM analyzes the issues and failures exposed in instruction evolution performed by the evol LLM, and Evolving Method Optimization, where the optimizer LLM addresses these issues to progressively develop an effective evolving method. The optimal evolving method is then used to convert the entire instruction dataset into more diverse and complex forms, facilitating improved instruction tuning.

📈2. Scaling Evol-Instruct with Arena Learning

With Auto Evol-Instruct, the evolutionary synthesis data of WizardLM-2 has scaled up from WizardLM-1 to dozens of domains, covering tasks in all aspects of large language models. This allows Arena Learning to train and learn from an almost infinite pool of high-difficulty instruction data, fully unlocking all the potential of Arena Learning.

1 reply

upvoted an article 5 months ago

Article

Welcome Gemma 2 - Google's new open LLM

Jun 27

• 124

updated 9 datasets 6 months ago