Skip to content
All tags

#huggingface

2 posts
aiguideReading NTU Yun-Nung Chen Applied Deep Learning

Chinese Extractive QA: Finding the Answer Span Among Four Paragraphs | NTU Yun-Nung Chen Applied Deep Learning Assignment 1

HW1 in ADL Fall 2025 gives a question and four Chinese paragraphs. The model first picks the relevant paragraph (paragraph selection, framed as four-way multiple choice), then marks the answer's start and end inside it (span selection), scored by Exact Match. The spec slides point you straight at Hugging Face's run_swag_no_trainer.py and run_qa_no_trainer.py. The simple baseline uses bert-base-chinese, length 512, effective batch size 2, and learning rate 3e-5, and both stages together take under three hours on an 8GB RTX 3070. The Kaggle leaderboard closed 9/29, and code plus report were due 10/1 on NTU COOL. Outside readers cannot get the Kaggle data or grading, but the task design, baseline settings, and five report questions are all usable for practice.

#ntu#ai-course#course-guide#homework#bert#question-answering#huggingface
techdeep-diveSelf-Hosted Inference

TGI: HuggingFace's LLM Inference Server, and Why It Entered Maintenance Mode

Text Generation Inference (TGI) is HuggingFace's own LLM inference server, built in Rust and Python. It pioneered continuous batching and Flash Attention in open-source inference engines. The GitHub repository was archived on March 21, 2026, and HuggingFace recommends migrating to vLLM or SGLang. TGI still matters: it defined the architectural baseline that successor engines inherited, and many HuggingFace Inference Endpoints still run it.

#tgi#huggingface#llm-serving#inference#gpu#self-hosted