Jaykef / min-patchnizerLinks
Minimal, clean code for video/image "patchnization" - a process commonly used in tokenizing visual data for use in a Transformer encoder.
☆11Updated last year
Alternatives and similar repositories for min-patchnizer
Users that are interested in min-patchnizer are comparing it to the libraries listed below
Sorting:
- Latent Large Language Models☆18Updated 9 months ago
- PyTorch Implementation of the paper "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training"☆23Updated last week
- implementation of https://arxiv.org/pdf/2312.09299☆20Updated 11 months ago
- This library supports evaluating disparities in generated image quality, diversity, and consistency between geographic regions.☆20Updated last year
- A library for simplifying fine tuning with multi gpu setups in the Huggingface ecosystem.☆16Updated 7 months ago
- Let's try and finetune the OpenAI consistency decoder to work for SDXL☆24Updated last year
- Create topological graph for image segments.☆22Updated 8 months ago
- Training hybrid models for dummies.☆21Updated 4 months ago
- Implementation of SoundtStream from the paper: "SoundStream: An End-to-End Neural Audio Codec"☆12Updated 4 months ago
- LLMs sitting on a council together to decide, by consensus, who among them is the best.☆15Updated 3 weeks ago
- ☆27Updated last year
- Make-A-Video Latent Diffusion Model☆18Updated last year
- Rust bindings for CTranslate2☆14Updated last year
- ☆13Updated 2 years ago
- Visual RAG using less than 300 lines of code.☆27Updated last year
- code for paper "Accessing higher dimensions for unsupervised word translation"☆21Updated last year
- Pixel Parsing. A reproduction of OCR-free end-to-end document understanding models with open data