CrownKira
Follow
Stars
🔥🔥First-ever hour scale video understanding models
Code and data releases for the paper -- DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory
📃 A better UX for chat, writing content, and coding with LLMs.
A guide that teach you enable hardware HEVC decoding & encoding for Chrome / Edge, or build a custom version of Chromium / Electron that supports hardware & software HEVC decoding and hardware HEVC…
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, le…
Free and source-available fair-code licensed workflow automation tool. Easily automate tasks across different services.
Build resilient language agents as graphs.
AIConfig is a config-based framework to build generative AI applications.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
DSPy: The framework for programming—not prompting—foundation models
Draft for ECMAScript Error Safe Assignment Operator
Auto_Jobs_Applier_AIHawk is a tool that automates the jobs application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in an automated and personalized way.
Chat with your documents using Vision Language Models. This repo implements an End to End RAG pipeline with both local and proprietary VLMs
Use late-interaction multi-modal models such as ColPali in just a few lines of code.
Code for explaining and evaluating late chunking (chunked pooling)
Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.
ReelsMaker is a Python-based/streamlit application designed to create captivating faceless videos for social media platforms like TikTok and YouTube.
[ECCV'24 Workshops Oral] DALDA: Data Augmentation Leveraging Diffusion Model and LLM with Adaptive Guidance Scaling
Statewide Visual Geolocalization in the Wild (ECCV 2024)
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
"Pooling And Attention: What Are Effective Designs For LLM-Based Embedding Models?"
Chat with any codebase in under two minutes | Fully local or via third-party APIs
🚀A modern, comprehensive, flexible design system and React UI library. 🎨 Provide more than 3000 Design Tokens, easy to build your design system. Make Semi Design to Any Design. 🧑🏻💻 Design to Code…
extract keywords from a corpus using pretrain LLM via Huggingface
we propose FlexEdit, an end-to-end image editing method that leverages both free-shape masks and language instructions for Flexible Editing.