shuhongwu
Follow
Stars
Open Source Application for Advanced LLM Engineering: interact, train, fine-tune, and evaluate large language models on your own computer.
CPU inference for the DeepSeek family of large language models in pure C++
Official Pytorch implementation for "IFORMER: INTEGRATING CONVNET AND TRANSFORMER FOR MOBILE APPLICATION" [ICLR 2025]
Open-Source, Free, and AI-Powered News in Short
A file manager built using Svelte and Wails. It has hotkeys that are modal just like Vim and NeoVim.
Minimalist LLM Framework in 100 Lines. Enable LLMs to Program Themselves.
Continual Learning of Large Language Models: A Comprehensive Survey
Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- H…
Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory
Personal Productivity Assistant is a revolutionary open-source application dedicating to enhancing individuals focus productivity. By utilizing locally hosted open AI model , it provides detailed i…
Witness the aha moment of VLM with less than $3.
Schola is a plugin for enabling Reinforcement Learning (RL) in Unreal Engine. It provides tools to help developers create environments, define agents, and connect to python-based RL frameworks such…
🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.
A lightweight TUI application to view and query tabular data files, such as CSV, TSV, and parquet.
A real-time silent speech recognition tool.
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
Generate Your Own Private Morning Radio for Commute
The goal of RamaLama is to make working with AI boring.
Fully open reproduction of DeepSeek-R1
Filter your current RSS feeds with AI customized recommendations.
A free, open-source SaaS app starter for React & Node.js with superpowers. Full-featured. Community-driven.
Everything you need to build state-of-the-art foundation models, end-to-end.