Get your documents ready for gen AI

High performance self-hosted photo and video management solution.

[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward

Efficient few-shot learning with Sentence Transformers

Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793

Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).

The fastest way to create an HTML app

aider is AI pair programming in your terminal

A fast, local neural text to speech system

🙌 OpenHands: Code Less, Make More

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.

LLM101n: Let's build a Storyteller

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

MARS5 speech model (TTS) from CAMB.AI

Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!

A benchmark for emotional intelligence in large language models

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

Evaling and unaligning Chinese LLM censorship

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Tools for merging pretrained large language models.

Instant voice cloning by MIT and MyShell.

The most no-nonsense, locally or API-hosted AI code completion plugin for Visual Studio Code - like GitHub Copilot but completely free and 100% private.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, an…