juyongjiang Goto Github PK

followers: 120.0 following: 327.0 repos: 263.0 gists: 2.0

Name: John

Type: User

Company: HKUST

Bio: PhD Student (Sep. 2022-Now) at HKUST. Working on NLP, with a focus on large language models and code generation

Twitter: JohnJia23050175

Location: Hong Kong

#!/usr/bin/python
# -- coding: utf-8 --


print('''
Hi there 👋. 
I am Juyong Jiang, a PhD student (Sep. 2022 - Now) at HKUST, under the supervision of Prof. Sunghun Kim.
My research interest is NLP, with a focus on large language models and code generation.
Follow me. 😄
''')

John's Projects

chinese-ocr

[python3.6] 运用tf实现自然场景文字检测,keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别

chinese-vicuna

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

cikm2020-s3rec

Code for CIKM2020 "S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization"

cocoapi

COCO API - Dataset @ http://cocodataset.org/

cocostuff

The official homepage of the COCO-Stuff dataset.

code-for-mamo

The code for paper MAMO: Memory-Augmented Meta-Optimization for Cold-start Recommendation

codegen-metrics

Replication package for evaluation of code generation metrics

codeintelligence

Code Intelligence

codesearchnet

Datasets, tools, and benchmarks for representation learning of code.

codeup

CodeUp: A Multilingual Code Generation Llama2 Model with Parameter-Efficient Instruction-Tuning on a Single RTX 3090

cold-start-recsys

Papers, codes , and framewroks that used in Recommender System to solve code-start challenge problem.

compositional-attention

Code to reproduce the results for Compositional Attention

conference_call_for_paper

2019-2020 International Conferences in Artificial Intelligence, Machine Learning, Computer Vision, Data Mining, Natural Language Processing and Robotics