Yanli Liu Journalist Profile

Articles

Vibronic Effects Analysis of the Substituent Effect on the Spectral Properties of the EMI and CPL of Three [7]Helicene Derivatives

Dec 26, 2024 | mdpi.com | Yanli Liu

This is an early access version, the complete PDF, HTML, and XML versions will be available soon. Open AccessArticle by Qiushuang Xu 1,*, Meishan Wang 2,* and Yanli Liu 3 1Department of Physics, Yantai University, Yantai 264005, China 2College of Integrated Circuits, Ludong University, Yantai 264005, China 3School of Physics and Optoelectronics Engineering, Ludong University, Yantai 264005, China *Authors to whom correspondence should be addressed.
Multi-Objective Planting Structure Optimisation in an Irrigation Area Using a Grey Wolf Optimisation Algorithm

Aug 14, 2024 | mdpi.com | Li Wu |Junfeng Tian |Yanli Liu |Yong Huei Wang

All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess.
Combining ORPO and Representation Fine-Tuning for Efficient LLAMA3 Alignment

Jun 23, 2024 | towardsdatascience.com | Yanli Liu

By Yanli Liu Achieving Better Results and Efficiency in Language Model Fine-TuningFine-tuning is one of the most popular techniques for adapting language models to specific tasks. However, in most cases, this will require large amounts of computing power and resources. Recent advances, among them PeFT, the parameter-efficient fine-tuning such as the Low-Rank Adaptation method, Representation Fine-Tuning, and ORPO ...
Why Representation Finetuning is the Most Efficient Approach Today?

May 26, 2024 | towardsdatascience.com | Yanli Liu

By Yanli Liu A Step-by-Step Guide to Representation Finetuning LLAMA3Do you know it's possible to fine-tune a Language Model using just a few parameters and a tiny dataset with as few as 10 data points? Well, it's not magic. Photo by Mrika Selimi on Unsplash
Building Local RAG Chatbots Without Coding Using LangFlow and Ollama

Apr 8, 2024 | medium.com | Yanli Liu

Building Local RAG Chatbots Without Coding Using LangFlow and OllamaA Quick Way to Prototype RAG Applications Based on LangChain⁤Remember the days when building a smart chatbot took months of coding? Frameworks like LangChain have definitely streamlined development, but hundreds of lines of code can still be a hurdle for those who aren’t programmers. ⁤Is there a simpler way ?
Building Local RAG Chatbots Without Coding Using LangFlow and Ollama

Apr 8, 2024 | towardsdatascience.com | Yanli Liu

Building Local RAG Chatbots Without Coding Using LangFlow and OllamaA Quick Way to Prototype RAG Applications Based on LangChain⁤Remember the days when building a smart chatbot took months of coding? Frameworks like LangChain have definitely streamlined development, but hundreds of lines of code can still be a hurdle for those who aren’t programmers. ⁤Is there a simpler way ?
Declutter Your Spending With Local AI Finance Insighter

Apr 7, 2024 | medium.com | Yanli Liu

A personalized and secure approach to analyzing financial data, providing tailored insights and recommendationsAs the spring season rolls in, bringing with it the tradition of house decluttering, I decided to use my Easter break to get a grip on my finances, cut costs, and formulate a better financial plan. The idea of asking ChatGPT or sharing my confidential data with OpenAI, Google, or any other AI solution provider didn’t sit well with me.
How to Generate Instruction Datasets from Any Documents for LLM Fine-Tuning

Mar 6, 2024 | medium.com | Yanli Liu

Generate high-quality synthetic datasets economically using lightweight librariesLarge Language Models (LLMs) are capable and general-purpose tools, but often they lack domain-specific knowledge, which is frequently stored in enterprise repositories. Fine-tuning a custom LLM with your own data can bridge this gap, and data preparation is the first step in this process. It is also a crucial step that can significantly influence your fine-tuned model’s performance.
How to Generate Instruction Datasets from Any Documents for LLM Fine-Tuning

Mar 6, 2024 | towardsdatascience.com | Yanli Liu

Generate high-quality synthetic datasets economically using lightweight librariesLarge Language Models (LLMs) are capable and general-purpose tools, but often they lack domain-specific knowledge, which is frequently stored in enterprise repositories. Fine-tuning a custom LLM with your own data can bridge this gap, and data preparation is the first step in this process. It is also a crucial step that can significantly influence your fine-tuned model’s performance.
The Future of Financial AI: Stock Sentiment Analysis with SLIM Models

Feb 27, 2024 | medium.com | Yanli Liu

How to perform complex multi-step analytics using LLMWare on CPUGenerative AI can go beyond simple question answering or simple summarization. For its true potential to be realized, it must be seamlessly integrated into end-to-end workflows, capable of conducting complex multi-step analytics, and generating sophisticated deliverables. This article will guide you through the intricate process of multi-step stock sentiment analysis.