Simple proxy worker for using ollama in cursor

Libraries and tools for interoperability between Hadoop-related open-source software and Google Cloud Platform.

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

Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and knowledge-based reasoning tasks.

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.

LLM based data scientist, AI native data application. AI-driven infinite thinking redefines BI.

A code-first agent framework for seamlessly planning and executing data analytics tasks.

Get up and running with Llama 3, Mistral, Gemma, and other large language models.

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

The official Python library for the OpenAI API

Benchmarks of approximate nearest neighbor libraries in Python

Unify Efficient Fine-tuning of 100+ LLMs

DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

PilotScope is a middleware to bridge the gaps of deploying AI4DB (Artificial Intelligence for Databases) algorithms into actual database systems.

Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. S…

Training LLMs with QLoRA + FSDP

Making large AI models cheaper, faster and more accessible

DLRover: An Automatic Distributed Deep Learning System

This playlab encompasses a multitude of projects crafted through the utilization of Large Language Models, showcasing the versatility and impact of these models across various applications.

Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-l…

Fast and memory-efficient exact attention

Easily compute clip embeddings and build a clip retrieval system with them

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models