Fine-tuning

Google Introduces Flan-T5: A Model for All NLP Tasks

by
Google Introduces Flan-T5: A Model for All NLP Tasks

MLNLP community is a well-known machine learning and natural language processing community both domestically and internationally, covering NLP graduate students, university professors, and researchers in enterprises.The vision of the community is to promote communication and progress between academia, industry, and enthusiasts in natural language processing and machine learning, especially for beginners. Reprinted from | NewBeeNLP … Read more

Decoding Performance Issues in Large Model Training, Fine-tuning, and Inference

by
Decoding Performance Issues in Large Model Training, Fine-tuning, and Inference

Source: Shi Zhi AI wisemodel This article contains 3335 words, and it is recommended to read in 7 minutes. This article introduces the benchmark tests conducted by the research teams from the Hong Kong University of Science and Technology and Beijing DaMo Technology on the performance of different sizes of LLMs across various GPU platforms. … Read more

Challenges and Alternatives to Catching Up with ChatGPT

by
Challenges and Alternatives to Catching Up with ChatGPT

MLNLP community is a well-known machine learning and natural language processing community both domestically and internationally, covering NLP master’s and doctoral students, university teachers, and researchers in enterprises. The vision of the community is to promote communication and progress between the academic and industrial communities of natural language processing and machine learning, especially for beginners. … Read more

Why Is Your Saved BERT Model So Large?

by
Why Is Your Saved BERT Model So Large?

Follow the public account “ML_NLP” Set as “Starred”, heavy content delivered first-hand! Produced by Machine Learning Algorithms and Natural Language Processing Original Column Author on Public Account Liu Cong School | NLP Algorithm Engineer A while ago, a friend asked me this question: the ckpt file size of the bert-base model provided by Google is … Read more

Stabilizing BERT Fine-tuning on Small Datasets

by
Stabilizing BERT Fine-tuning on Small Datasets

Follow our public account “ML_NLP“ Set as “Starred“, heavy content delivered first! Author:Qiu Zhenyu (Algorithm Engineer, Huatai Securities Co., Ltd.) Zhihu Column:My AI Journey Recently, I came across a paper titled “Revisiting Few-sample BERT Fine-tuning”. The paper has just been released on arXiv, and although it hasn’t attracted much attention yet, I found it very … Read more

Understanding BERT and HuggingFace Transformers Fine-Tuning

by
Understanding BERT and HuggingFace Transformers Fine-Tuning

This article is also published on my personal website, where the formula images display better. Welcome to visit: https://lulaoshi.info/machine-learning/attention/bert Since the emergence of BERT (Bidirectional Encoder Representations from Transformer) [1], a new paradigm has opened up in the field of NLP. This article mainly introduces the principles of BERT and how to use the transformers … Read more

Integrating Knowledge into Text Classification with KPT

by
Integrating Knowledge into Text Classification with KPT

Source: TsinghuaNLP, Deep Learning Natural Language Processing This article is about 2400 words long and is recommended to be read in 5 minutes. This article uses a knowledge base to expand and improve label words, achieving better text classification results. Background Using Prompt Learning for text classification tasks is an emerging method that leverages pre-trained … Read more

CMU Liu Pengfei: The Fourth Paradigm of NLP

by
CMU Liu Pengfei: The Fourth Paradigm of NLP

Written by | Liu Pengfei Edited by | Jia Wei Source | AI Technology Review In the past two years, the research paradigm based on pre-training + fine-tuning has rapidly swept the entire field of NLP. This research paradigm is widely recognized as a revolutionary paradigm in NLP research, with previous paradigms including “expert systems,” … Read more

Prompt, RAG, Fine-Tuning, or Training From Scratch? Choosing the Right Generative AI Approach

by
Prompt, RAG, Fine-Tuning, or Training From Scratch? Choosing the Right Generative AI Approach

Source: DeepHub IMBA This article is approximately 2600 words and suggests a 5-minute reading time. This article will attempt to provide recommendations for choosing the correct generative AI methods based on some common quantifiable metrics. Generative AI is rapidly evolving, and many people are trying to use this technology to solve their business problems. Generally, … Read more

In-Depth Guide to Prompt Learning and Tuning

by
In-Depth Guide to Prompt Learning and Tuning

MLNLP community is a well-known machine learning and natural language processing community in China and abroad, targeting NLP graduate students, university teachers, and corporate researchers. The vision of the community is to promote communication and progress between the academia and industry of natural language processing and machine learning, especially for the advancement of beginners. Reprinted … Read more