Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Creating a bot that harnesses the power of LLM's like Llama 2 to convert natural language queries to SQL queries using various techniques like in context learning and PEFT

scripts and baselines for Spider: Yale complex and cross-domain semantic parsing and text-to-SQL challenge

Benchmark baseline for retrieval qa applications

Text-to-SQL Generation for Question Answering on Electronic Medical Records

Data for the Chat With Your Data benchmark.

A financial agent, built entirely with LangChain!

Financial datasets for LLMs 🧪

Financial agent + generative UI

The official Meta Llama 3 GitHub site

Unsupervised text tokenizer for Neural Network-based text generation.

Agentic RAG with Langchain, Qdrant and CrewAI

chatbot_ner: Named Entity Recognition for chatbots.

Code implement reposity of Paper HiQA

This is the code repo for our paper "Revealing the Treasures of Knowledge via Active Learning".

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

llama3 implementation one matrix multiplication at a time

Data processing with ML and LLM

Parse files for optimal RAG

⚡FlashRAG: A Python Toolkit for Efficient RAG Research

LangChain + Next.js starter template

The easiest way to use Agentic RAG in any enterprise

SUQL: Conversational Search over Structured and Unstructured Data with LLMs

A web app built with Streamlit that allows you to chat with your databases using a GPT model.