Pinned Repositories
01
The open-source language model computer
3detr
Code & Models for 3DETR - an End-to-end transformer model for 3D object detection
A2L
[ICLR 2020] Learning to Move with Affordance Maps 🗺️🤖💨
Access-2021
ACE_Framework
Public repo for my latest and greatest cognitive architecture ACE (Autonomous Cognitive Entity) Framework
ACF_perception
Implementation of paper "Manipulation-Oriented Object Perception in Clutter through Affordance Coordinate Frames".
AD-Census
AD-Census立体匹配算法，**学者Xing Mei等人研究成果（Respect！），算法效率高、效果出色，适合硬件加速，Intel RealSense D400 Stereo模块算法。完整实现，代码规范，注释清晰，欢迎star！
functionary
Chat language model that can interpret and execute functions/plugins
llama.openvino
This sample shows how to implement a llama-based model with OpenVINO runtime
SayCan_experimental
Proof of concept of the SayCan project applying on real UR5 robot
jjhw's Repositories
jjhw/ADAS
Automated Design of Agentic Systems
jjhw/Agent-E
Agent driven automation starting with the web. Discord: https://discord.gg/wgNfmFuqJF
jjhw/anyclassifier
One Line To Build Any Classifier Without Data
jjhw/Controllable-RAG-Agent
This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks.
jjhw/CosyVoice
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
jjhw/Depth-Anything-V2
Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
jjhw/embedchain
Framework to easily create LLM powered bots over any dataset.
jjhw/erag
a RAG tool with lexical, semantic, text and knowledge graph searches as well with conversation context
jjhw/FastGPT
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, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.
jjhw/fish-speech
Brand new TTS solution
jjhw/Golden-Retriever
A framework for high-fidelity retrieval augmented generation in industrial knowledge bases. Integrates jargon identification, context recognition, and question augmentation to overcome challenges in specialized domains. Extensible architecture for efficient querying and answering of complex, domain-specific questions.
jjhw/gptlint
A linter with superpowers! 🔥 Use LLMs to enforce best practices across your codebase.
jjhw/graph-llm-asynchow-plan
Code and dataset repo for ICML-2024 paper Graph-enhanced Large Language Models in Asynchronous Plan Reasoning.
jjhw/graphrag-accelerator
One-click deploy of a Knowledge Graph powered RAG (GraphRAG) in Azure
jjhw/HiRED
An early token dropping algorithm to improve inference efficiency for Vision-Lanauge Models with high-resolution images under resource constraints.
jjhw/InternLM-XComposer
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
jjhw/llama-agentic-system
Agentic components of the Llama Stack APIs
jjhw/MathBlackBox
jjhw/MoA-MLC-Chat
A lightweight version on the MoA architecture using MLC providing a much faster experience
jjhw/MoA-Ollama-ChatApp
This is the Mixture-of-Agents (MoA) concept, adapted from the original work by Together Computer. My version is tailored for local model usage and features a user-friendly Gradio interface.
jjhw/Mycomind-Daemon-Ollama-Mixture-of-Memory-RAG-Agents
Mycomind Daemon: A mycelium-inspired, advanced Mixture-of-Memory-RAG-Agents (MoMRA) cognitive assistant that combines multiple AI models with memory, RAG and Web Search for enhanced context retention and task management.
jjhw/omni-engineer
jjhw/parler-tts
Inference and training library for high-quality TTS models.
jjhw/parsera
Lightweight library for scraping web-sites with LLMs
jjhw/prismatic-vlms
A flexible and efficient codebase for training visually-conditioned language models (VLMs)
jjhw/sapiens
High-resolution models for human tasks.
jjhw/ShiftAddLLM
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
jjhw/storm
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
jjhw/Unique3D
Official implementation of Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
jjhw/whisper-medusa
Whisper with Medusa heads