Pinned Repositories
1-billion-word-language-modeling-benchmark
Automatically exported from code.google.com/p/1-billion-word-language-modeling-benchmark
AgeGenderDeepLearning
AgentGPT
🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.
ai-chatbot-framework
A python chatbot framework with Natural Language Understanding and Artificial Intelligence.
ai-edu
AI education materials for Chinese students, teachers and IT professionals.
AI_Challenger
AI Challenger, a platform for open datasets and programming competitions to artificial intelligence (AI) talents around the world.
ailab
Experience, Learn and Code the latest breakthrough innovations with Microsoft AI
ieturk
Intuitive Annotation Tool for Information / Named Entity Recognition using localturk / Amazon Mechanical Turk
NLPer-Arsenal
收录NLP相关竞赛经验贴（当前赛事、往期赛事、训练赛）、NLP会议时间、常用自媒体、GPU推荐等，持续更新中
huguanglong's Repositories
huguanglong/anything-llm
The all-in-one Desktop & Docker AI application with full RAG and AI Agent capabilities.
huguanglong/api-for-open-llm
Openai style api for open large language models, using LLMs just as chatgpt! Support for LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, Xverse, SqlCoder, CodeLLaMA, ChatGLM, ChatGLM2, ChatGLM3 etc. 开源大模型的统一后端接口
huguanglong/BitNet
Official inference framework for 1-bit LLMs
huguanglong/ChatTTS
ChatTTS is a generative speech model for daily dialogue.
huguanglong/detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
huguanglong/elasticsearch
Free and Open Source, Distributed, RESTful Search Engine
huguanglong/Flowise
Drag & drop UI to build your customized LLM flow
huguanglong/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
huguanglong/hallucination-leaderboard
Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents
huguanglong/HippoRAG
HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.
huguanglong/LightRAG
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
huguanglong/LLaMA-Omni
LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.
huguanglong/LLMs-from-scratch
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
huguanglong/marker
Convert PDF to markdown quickly with high accuracy
huguanglong/MemGPT
Create LLM agents with long-term memory and custom tools 📚🦙
huguanglong/minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
huguanglong/mlx
MLX: An array framework for Apple silicon
huguanglong/moshi
huguanglong/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
huguanglong/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
huguanglong/qdrant
Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
huguanglong/ragflow
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
huguanglong/reader
Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/
huguanglong/realm-java
Realm is a mobile database: a replacement for SQLite & ORMs
huguanglong/sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
huguanglong/supermemory
Build your own second brain with supermemory. It's a ChatGPT for your bookmarks. Import tweets or save websites and content using the chrome extension.
huguanglong/unsloth
Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
huguanglong/unstructured
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
huguanglong/whisper
Robust Speech Recognition via Large-Scale Weak Supervision
huguanglong/YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/