Speed Up Large Model Training by 40% with One GPU and Few Lines of Code!

Speed Up Large Model Training by 40% with One GPU and Few Lines of Code!

Mingmin from Aofeisi Quantum Bit | Public Account QbitAI It must be said that to enable more people to use large models, the tech community is indeed coming up with various tricks! Not open enough models? Some people are taking matters into their own hands to create free open-source versions. For example, the recently popular … Read more

Google & Hugging Face: The Strongest Language Model Architecture for Zero-Shot Capability

Google & Hugging Face: The Strongest Language Model Architecture for Zero-Shot Capability

This article is approximately 2000 words long and takes about 5 minutes to read. If the goal is the model's zero-shot generalization capability, the decoder structure + language model task is the best; if multitask finetuning is also needed, the encoder-decoder structure + MLM task is the best. From GPT-3 to prompts, more and more … Read more

5-Minute NLP: Introduction to Hugging Face Classes and Functions

5-Minute NLP: Introduction to Hugging Face Classes and Functions

Source: Deephub Imba This article is approximately 2200 words long and is recommended for a 9-minute read. It includes an overview of its main classes and functions along with some code examples. It can serve as an introductory tutorial for this library. Mainly includes Pipeline, Datasets, Metrics, and AutoClasses Hugging Face is a very popular … Read more

Fine-Tuning TrOCR for Curved and Blurry Text Recognition

Fine-Tuning TrOCR for Curved and Blurry Text Recognition

Author: Sovit Rath Translated by: ronghuaiyang Introduction This article fine-tunes the TrOCR model on a dataset of curved and blurry text, analyzing the code and training results at each step. TrOCR (Transformer based Optical Character Recognition) model is one of the best OCR models. In previous articles, we analyzed how well this model performs on … Read more

Introduction and Usage of TrOCR: Transformer-Based OCR

Introduction and Usage of TrOCR: Transformer-Based OCR

Author: Sovit Rath Translator: ronghuaiyang Introduction This article introduces the structure and usage of TrOCR, teaching step by step from each line of code. Optical Character Recognition (OCR) has seen several innovations in recent years. Its impact on retail, healthcare, banking, and many other industries is tremendous. Despite its long history and some state-of-the-art models, … Read more

Llama Model Utility Toolkit

Llama Model Utility Toolkit

Project Overview Llama is an easily accessible, open large language model (LLM) designed for developers, researchers, and businesses to build, experiment, and responsibly scale their generative AI ideas. As part of the foundational system, it is a cornerstone for global social innovation. Several key aspects: Open Access: Easy access to cutting-edge large language models, promoting … Read more

How to Use BERT and GPT-2 in Your Models

How to Use BERT and GPT-2 in Your Models

Recommended by New Intelligence Source: Zhuanzhi (ID: Quan_Zhuanzhi) Editor: Sanshi [New Intelligence Guide] In the field of NLP, various advanced tools have emerged recently. However, practice is the key, and how to apply them to your own models is crucial. This article introduces this issue. Recently in NLP, various pre-trained language models like ELMO, GPT, … Read more

Building Language Applications with Hugging Face Transformers

Building Language Applications with Hugging Face Transformers

Hugging Face is a chatbot startup based in New York, focusing on NLP technology, with a large open-source community. Especially, the open-source natural language processing and pre-trained model library, Transformers, has been downloaded over a million times and has more than 24,000 stars on GitHub. Transformers provides a large number of state-of-the-art pre-trained language model … Read more

Hugging Face Official Course Launched: Free NLP Training

Hugging Face Official Course Launched: Free NLP Training

Machine Heart reports Editor: Du Wei The Hugging Face NLP course is now live, and all courses are completely free. Those in the NLP field should be very familiar with the renowned Hugging Face, a startup focused on solving various NLP problems that has brought many beneficial technical achievements to the community. Last year, the … Read more

Qwen 1.5 Open Source! Best Practices for Magic Adaptation!

Qwen 1.5 Open Source! Best Practices for Magic Adaptation!

In recent months, the Tongyi Qianwen team has been working hard to explore how to build a ‘good’ model while optimizing the developer experience. Just before the Chinese New Year, the Tongyi Qianwen team shared the next version of the Qwen open-source series, Qwen 1.5. Qwen 1.5 has open-sourced six sizes of foundational and chat … Read more