jasonqi146,Wonderplex,github

🎓 M.S. in Intelligent Information Systems
Carnegie Mellon University, School of Computer Science
🎓 B.S in Computer Science, B.A. in Math and Economics
Georgia Institute of Technology, Emory University Dual Degree
📫 Contact: [email protected] |
🛠️ Skills: Python, Java, C++, JavaScript, AWS, Docker, PyTorch, TensorFlow, GAN, XGBoost, Transformer
💼 Experience:
- Intuit Inc., Software Engineer Intern (May - Aug 2023)
  Developed scalable systems for tax form de-duplication, saving $2M annually.
- Intuit Inc., Machine Learning Engineer Intern (Jun - Aug 2022)
  Built a high-performance image captioning model using AWS and PyTorch.
🌟 Recent Projects:
- Chinese FLAN-T5 Contributed to LLM instruction in Chinese and multiple languages.
- Amex Default Prediction (Kaggle Top 1.6%) Enhanced financial feature models using LGBM and XGBoost.
📄 Publications:
- Sotopia-π: Interactive Learning of Socially Intelligent Language Agents (Under review, ACL 2024)
- Sotopia: Interactive Evaluation for Social Intelligence in Language Agents (Accepted, ICLR 2024)

Wonderplex's Projects

albef

Code for ALBEF: a new vision-language pre-training method

ameft

AMEFT: Aggressive Memory Efficient Fine Tuning

cogvlm

a state-of-the-art-level open visual language model | 多模态预训练模型

decodingtrust

A Comprehensive Assessment of Trustworthiness in GPT Models

fastchatforsotopia

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

figaro

Source code for "FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control"

jasonqi146.github.io

A beautiful, simple, clean, and responsive Jekyll theme for academics

llama-factory

Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)

lm-evaluation-harness

A framework for few-shot evaluation of language models.

This repository contains code and tooling for the Abacus.AI LLM Context Expansion project. Also included are evaluation scripts and benchmark tasks that evaluate a model’s information retrieval capabilities with context expansion. We also include key experimental results and instructions for reproducing and building on them.

Recommend Projects