Ongoing research training transformer language models at scale, including: BERT & GPT-2

Ongoing research training transformer models at scale

Integrating Neo4j database into langchain ecosystem

Geppetto: Advanced Slack bot using multiple AI models for interactive conversations and creative image generation. Enhances Slack with automated responses and intelligent dialogues, supporting flex…

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

A high-throughput and memory-efficient inference and serving engine for LLMs

General technology for enabling AI capabilities w/ LLMs and MLLMs

Minimal, clean, code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

👁️ + 💬 + 🎧 = 🤖 Curated list of top foundation and multimodal models! [Paper + Code]

Train transformer language models with reinforcement learning.

A curated list of awesome Machine Learning frameworks, libraries and software.

🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

LlamaIndex (formerly GPT Index) is a data framework for your LLM applications

Converts text input or URL into knowledge graph and displays

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!

Build ChatGPT over your data, all with natural language

Providing enterprise-grade LLM-based development framework, tools, and fine-tuned models.

Open source platform for the machine learning lifecycle

Langchain + Docker + Neo4j + Ollama

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

Come join the movement to make the world's best open source GPT led by H2O.ai

🔮 SuperDuperDB: Bring AI to your database: Integrate, train and manage any AI models and APIs directly with your database and your data.

Deep Learning for humans

⚡ Building applications with LLMs through composability ⚡

OpenChat: Advancing Open-source Language Models with Imperfect Data