This is the repo for our new project Highly Accurate Dichotomous Image Segmentation

High-resolution models for human tasks.

build-once run-anywhere c library

Distribute and run LLMs with a single file.

Best practice for training LLaMA models in Megatron-LM

Minimalistic large language model 3D-parallelism training

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

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

DataComp for Language Models

[NeurIPS'24 Spotlight] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 whil…

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

Sample code and notebooks for Generative AI on Google Cloud, with Gemini on Vertex AI

Ongoing research training transformer models at scale

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

CoreNet: A library for training deep neural networks

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

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Code and Data for "Long-context LLMs Struggle with Long In-context Learning"

LLM training in simple, raw C/CUDA

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

MLX: An array framework for Apple silicon

Code examples and resources for DBRX, a large language model developed by Databricks

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

✨ QR Code encoder (Go)

ZXing ("Zebra Crossing") barcode scanning library for Java, Android

Fast and memory-efficient exact attention