🏗️ Building on HF

Huang Liang Hsun PRO

lianghsun

103 14 268

https://www.lianghsun.dev

AI & ML interests

Founder of 𝗧𝘄𝗶𝗻𝗸𝗹𝗲 𝗔𝗜. Focused on applying deep learning in legal and scientific domains, with expertise in NLP and model fine-tuning.

Recent Activity

updated a dataset about 21 hours ago

lianghsun/ly-ivod-asr-zhtw

updated a dataset about 21 hours ago

lianghsun/ultra-fineweb-l3-en-zhtw

published a dataset 2 days ago

lianghsun/ly-ivod-asr-zhtw

View all activity

Organizations

upvoted a collection 13 days ago

📚 LLM pretraining datasets

Collection

A collection of datasets for LLM pretraining • 9 items • Updated May 5, 2025 • 32

upvoted 2 collections 9 months ago

🤗 Fine-zhtw

Collection

Fine-zhtw is a Traditional Chinese (zh-TW) collection inspired by Hugging Face’s Fine series, built with mostly self-designed methods. • 6 items • Updated May 6 • 2

🌟 T1 Series

Collection

Instruction-tuned Gemma-3 models optimized for agentic workflows in Traditional Chinese. • 6 items • Updated Jul 22 • 4

upvoted a collection about 1 year ago

Vision Language Models Papers 🖼️💬📝

Collection

Papers about vision-language models, most important ones are on top of the list. • 27 items • Updated Apr 30, 2024 • 40

upvoted an article over 1 year ago

Article

Efficient Deep Learning: A Comprehensive Overview of Optimization Techniques 👐 📚

Isayoften

•

Aug 26, 2024

• 95

upvoted 2 collections over 1 year ago

🧠 Traditional Chinese Reasoning Datasets

Collection

A curated collection of datasets designed to evaluate and train reasoning capabilities in Traditional Chinese across various domains. • 3 items • Updated May 6 • 9

📋 Eval Logs

Collection

Benchmark log generated with Twinkle Eval, recording the model's outputs for each prompt. • 3 items • Updated May 6 • 4

upvoted an article over 1 year ago

Article

Open R1: Update #3

open-r1

•

Mar 11, 2025

• 297

upvoted a collection almost 2 years ago

chinese-dataset

Collection

收藏夹 • 8 items • Updated Mar 2 • 2

upvoted a paper almost 2 years ago

Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs

Paper • 2410.10739 • Published Oct 14, 2024 • 4

upvoted a collection almost 2 years ago

MobileLLM

Collection

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 49 items • Updated Mar 2 • 139

upvoted 2 collections about 2 years ago

Taiwan-Legal-Bench

Collection

This repository offers a dataset for evaluating legal models based on Taiwan’s laws, including legal questions, provisions, and case law. • 1 item • Updated Apr 11 • 1

⚖️ Llama-3.2-Taiwan-Legal

Collection

Based on the lianghsun/Llama-3.2-Taiwan-*B model, the fine-tuning was conducted using datasets related to the laws and judgments of Taiwan. • 2 items • Updated Mar 2 • 1

Huang Liang Hsun PRO

AI & ML interests

Recent Activity

Organizations

lianghsun's activity

Efficient Deep Learning: A Comprehensive Overview of Optimization Techniques 👐 📚

Open R1: Update #3