Getting Started with Hugging Face

Getting Started with Hugging Face

This Article Covers The main contents of this article include: What is Hugging Face and what does it offer Using Hugging Face models (Transformers library) Using Hugging Face datasets (Datasets library) Introduction to Hugging Face Similar to GitHub, Hugging Face is a hub (community). It can be considered the GitHub of the machine learning world. … Read more

Detailed Explanation of HuggingFace BERT Source Code

Detailed Explanation of HuggingFace BERT Source Code

Follow the official account “ML_NLP“ Set as “Starred“, heavy content delivered first-hand! Reprinted from | PaperWeekly ©PaperWeekly Original · Author | Li Luoqiu School | Master’s Student at Zhejiang University Research Direction | Natural Language Processing, Knowledge Graphs This article records my understanding of the code in the HuggingFace open-source Transformers project. As we all … Read more

LlamaIndex: A Python Library for Building Intelligent Query Systems

LlamaIndex: A Python Library for Building Intelligent Query Systems

In the world of artificial intelligence and machine learning, intelligent query systems have become an indispensable part. Whether in search engines, recommendation systems, or customer service chatbots, we need a system that can intelligently understand and process user queries. LlamaIndex (formerly known as GPT Index) is a powerful Python library specifically designed to help developers … Read more

RAG: From Theory to LlamaIndex Practice (Detailed Version)

RAG: From Theory to LlamaIndex Practice (Detailed Version)

Abstract Large language models (LLMs) have demonstrated impressive capabilities. However, this does not mean they are error-free; anyone who has experienced ChatGPT’s “hallucinations” can attest to that. Retrieval Augmented Generation (RAG) is a framework designed to make LLMs more reliable by extracting relevant, up-to-date data directly related to user queries. In this article, I analyze … Read more

BERT Lightweight: Optimal Parameter Subset Bort at 16% Size

BERT Lightweight: Optimal Parameter Subset Bort at 16% Size

Zheng Jiyang from Aofeisi QbitAI Report | WeChat Official Account QbitAI Recently, the Amazon Alexa team released a research achievement: researchers performed parameter selection on the BERT model, obtaining the optimal parameter subset of BERT—Bort. The research results indicate that Bort is only 16% the size of BERT-large, but its speed on CPU is 7.9 … Read more

BERT: Training Longer and with More Data to Return to SOTA

BERT: Training Longer and with More Data to Return to SOTA

Machine Heart Report Contributors: Si Yuan, Qian Zhang The championship throne of XLNet has not yet warmed up, and the plot has once again taken a turn. Last month, XLNet comprehensively surpassed BERT on 20 tasks, creating a new record for NLP pre-training models and enjoyed a moment of glory. However, now, just a month … Read more

EdgeBERT: Limit Compression, 13 Times Lighter Than ALBERT!

EdgeBERT: Limit Compression, 13 Times Lighter Than ALBERT!

Machine Heart Reprint Source: Xixiaoyao’s Cute Selling House Author: Sheryc_Wang Su There are two types of highly challenging engineering projects in this world: the first is to maximize something very ordinary, like expanding a language model to write poetry, prose, and code like GPT-3; while the other is exactly the opposite, to minimize something very … Read more

Understanding Transformers: A Comprehensive Guide

Understanding Transformers: A Comprehensive Guide

This article is the first in a series produced by Big Data Digest and Baidu NLP. Baidu NLP is committed to the mission of “understanding language, possessing intelligence, and changing the world”. It conducts technical research and product applications in areas including natural language processing, machine learning, and data mining, leading the development of artificial … Read more

Further Improvements to GPT and BERT: Language Models Using Transformers

Further Improvements to GPT and BERT: Language Models Using Transformers

Selected from arXiv Authors: Chenguang Wang, Mu Li, Alexander J. Smola Compiled by Machine Heart Participation: Panda BERT and GPT-2 are currently the two most advanced models in the field of NLP, both adopting a Transformer-based architecture. A recent paper from Amazon Web Services proposed several new improvements to Transformers, including architectural enhancements, leveraging prior … Read more

LRC-BERT: Contrastive Learning for Knowledge Distillation

LRC-BERT: Contrastive Learning for Knowledge Distillation

New Intelligence Report Author: Gaode Intelligent Technology Center [New Intelligence Guide]The research and development team of Gaode Intelligent Technology Center designed a contrastive learning framework for knowledge distillation in their work, and proposed COS-NCE LOSS based on this framework. This paper has been accepted by AAAI 2021. NLP (Natural Language Processing) plays an important role … Read more