Fine Tuning is a cost-efficient way of preparing a model for specialized tasks. Fine-tuning reduces required training time as well as training datasets. We have open-source pre-trained models. Hence, we do not need to perform full training every time we create a model.

[ICML 2023] Official code for our paper: 'Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models'

LLM evaluation framework

Fine tune codellama-7b-hf to achieve natural language to SQL ability

Project proposal for solving the "Talk to your data" task at hackathon "HackYeah 2023"

Polish translation of spider dataset.

a framework for querying data using natural language

Look Awry is an Text to SQL application with local Ai, ensuring privacy.

A natural language querying system for Premier League stats

Large Language Models - Text2SQL Project

Use GPT to generate SQL

This project uses the open-source model Mixtral 8x7B Instruct, deployed in Amazon SageMaker or invoked via API on Amazon Bedrock, to enable users to chat with their database using natural language, without writing any code or SQL query.

Nesse repositório, eu sumarizo os casos de uso de chatGPT e LangChain que tenho estudado

Text2SQL project comparing different LLM models

A basic Text2SQL App, powered by Langchain and OpenAI.

Data Neuron is a powerful framework that enables you to build text-to-SQL applications with an easily maintainable semantic layer. Whether you're creating customer-facing chatbots, internal Slack bots for analytics, or other data-driven applications, Data Neuron provides the tools to make your data accessible through natural language

Python 3 reimplementation of SyntaxSQLNet, including several improvements

Using Database Rule for Weak Supervised Text-to-SQL Generation https://arxiv.org/abs/1907.00620

This repo provides sample code for improving RAG applications with rich data sources including SQL Warehouses and documents analysed with Azure Document Intelligence