xvjiarui
Follow
Highlights
- Pro
Stars
code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"
A flexible and efficient codebase for training visually-conditioned language models (VLMs)
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
GRiT: A Generative Region-to-text Transformer for Object Understanding (https://arxiv.org/abs/2212.00280)
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
Making large AI models cheaper, faster and more accessible
A collection of libraries to optimise AI model performances
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
An open-source framework for training large multimodal models.
GPT4All: Chat with Local LLMs on Any Device
Easily create large video dataset from video urls
Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]
[CVPR 2023] Official Implementation of X-Decoder for generalized decoding for pixel, image and language
Zero-shot Image-to-Image Translation [SIGGRAPH 2023]
COYO-700M: Large-scale Image-Text Pair Dataset
[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
Unofficial implementation of "Prompt-to-Prompt Image Editing with Cross Attention Control" with Stable Diffusion
A playbook for systematically maximizing the performance of deep learning models.
Demystify RAM Usage in Multi-Process Data Loaders
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
LAVIS - A One-stop Library for Language-Vision Intelligence
Hackable and optimized Transformers building blocks, supporting a composable construction.