Expert Specialized Fine-Tuning

A professional fine-tuning tool for customizing large language models.

CommonProductProgrammingLarge Language ModelsFine-Tuning

Expert Specialized Fine-Tuning (ESFT) is an efficient fine-tuning method for large language models (LLMs) with a Mixture-of-Experts (MoE) architecture. It optimizes model performance by adjusting only the task-related parts, improving efficiency while reducing resource and storage usage.

Install dependencies and download necessary adapters for a quick start.
Use the eval.py script to evaluate model performance on different datasets.
Use the get_expert_scores.py script to calculate the score of each expert based on the evaluation dataset.
Use the generate_expert_config.py script to generate a configuration to convert a MoE model trained only on task-related tasks.

ESFT is suitable for researchers and developers who need to customize fine-tune large language models. It can help them improve model performance on specific tasks while reducing resource consumption.

Researchers use ESFT to fine-tune models to improve performance on natural language processing tasks.
Developers utilize ESFT to optimize models to adapt to specific industry language processing needs.
Educational institutions adopt ESFT to customize teaching assistant models
enhancing teaching interactivity.

1. Clone or download the ESFT project to your local machine.
2. Enter the esft directory and install the required dependencies.
3. Download necessary adapters to adapt to different large language models.
4. Use the eval.py script to evaluate model performance on a specific dataset.
5. Based on the evaluation results

Visit

Expert Specialized Fine-Tuning Visit Over Time

Monthly Visits

503747431

Bounce Rate

37.31%

Page per Visit

5.7

Visit Duration

00:06:44

Expert Specialized Fine-Tuning Visit Trend

Expert Specialized Fine-Tuning Visit Geography

Expert Specialized Fine-Tuning Traffic Sources

Expert Specialized Fine-Tuning Alternatives

AIKit — A one-stop solution for hosting, deploying, building, and fine-tuning open-source large language models.

Programming•Open-source•Large Language Models

150

OneGen — An efficient single-pass unified generation and retrieval framework suitable for large language models.

Programming•Natural Language Processing•Large Language Models

Open Source LLM Tools — A collection of open-source large language model tools.

Productivity•AI Tools•Open Source

PresentationGen — A SpringBoot Web application that utilizes large language models to generate PPT files.

Productivity•Automation•Presentation

Shire — An AI programming agent language that facilitates communication between large language models (LLMs) and integrated development environments (IDEs) for automated programming.

Programming•AI Programming•Automation

PromptChainer — A free and fast prompt chain generator

Productivity•Artificial Intelligence•Automation

LongCite — Generates fine-grained citations for large language models in long text question answering.

Programming•Long Text Question Answering•Citation Generation

LongLLaVA — Efficiently extending multimodal large language models to 1,000 images.

Image•Multimodal Learning•Image Processing

iText2KG — Incrementally build knowledge graphs using large language models.

Productivity•Knowledge Graph•Natural Language Processing

ChatMLX — A high-performance MacOS chat application based on large language models.

chatting•Chat•Large Language Models

EAGLE — Exploration of the design space for multimodal large language models

Programming•Multimodal Learning•Large Language Models

252

Seed-ASR — Speech recognition technology based on large language models.

Others•Speech Recognition•Large Language Models

264

Phi-3.5-mini-instruct — A lightweight, multilingual advanced text generation model

Programming•Text Generation•Multilingual

parsera — A lightweight Python library for web scraping using large language models.

Programming•Python•Data Scraping

Data-Juicer — A one-stop data processing system that provides high-quality data for large language models.

Productivity•Machine Learning•Data Science

174

RAGFoundry — A framework for enhancing retrieval-augmented generation tasks with LLMs.

Programming•Natural Language Processing•Fine-tuning

Finetune — A platform for fine-tuning AI intelligent agents.

InternationalSelection•Intelligent Agents•Fine-tuning

MindSearch — An open-source AI search engine framework with performance comparable to Perplexity.ai Pro.

Programming•Search•Transformer

2094

Meta-Llama-3.1-70B — A large multilingual text generation model with 70 billion parameters.

Productivity•Large Language Model•Multilingual

360

ICSFSurvey — A deep dive into the internal consistency and self-feedback of large language models.

Programming•Internal Consistency•Self-Feedback

DCLM — Comprehensive framework for building and training large language models

Programming•Large language models•Dataset construction

Praison AI — Low Code Multi-Agent System Framework

Programming•Low Code•Multi-Agent System

102

AMchat — Intelligent assistant for solving higher-level mathematics problems

Education•Higher-Level Mathematics•Large Language Model

132

Benchmarking API Performance of Large Language Models — In-depth analysis of key metrics like TTFT and TPS

Others•Performance Comparison•API Service

390

EmoLLM — A mental health large language model supporting the mental health counseling pathway.

Education•Mental Health•Mental Counseling

522

Best AI Websites & Tools