ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)
Repository Index
142,273 visible repositories in the index
1,465–1,488 of 1,943 · Most stars
Cookiecutter template for FastAPI projects using: Machine Learning, uv, Github Actions and Pytests
[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
- computer-vision
- multimodal-large-language-models
- long-video-understanding
- llama
High Accuracy and efficiency multi-task fine-tuning framework for Code LLMs. This work has been accepted by KDD 2024.
- multi-task-learning
- multi-task-fine-tuning
- multi-model-support
- customizable
Grounded search engine (i.e. with source reference) based on LLM / ChatGPT / OpenAI API. It supports web search, file content search etc.
LLMFlows - Simple, Explicit and Transparent LLM Apps
- ai
- llm
- llm-inference
- llmops
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
All-in-one offensive security toolbox with AI agent and MCP architecture. Integrates tools like Nmap, Metasploit, FFUF, SQLMap. Enables pentesting, bug bounty hunting, threat hunting, and reporting. RAG-based responses with local knowledge base support.
This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]
Large-Scale Visual Representation Model
- large-sacle-pretrained-model
- laion400m
- vision-transformer
- embodied-artificial-intelligence
Haru: a low-latency, multilingual, full-duplex spoken dialogue model
Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.
This repo is unofficial ChatGPT api. It is based on Daniel Gross's WhatsApp GPT
🔥🔥🔥 [NeurIPS2025] MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem
这是一个 LangChain 1.0 和 LangGraph 1.0 的学习仓库,学习如何进行agent开发,涵盖从基础概念到实战项目的完整学习路径。
基于自然语言理解与机器学习的聊天机器人,支持多用户并发及自定义多轮对话
- nlp
- question-answering
- context
- nlu
VectorFlow is a high volume vector embedding pipeline that ingests raw data, transforms it into vectors and writes it to a vector DB of your choice.
TranslatedSprix AI at 屿智同行 (Yuzhi Tongxing, "island wisdom traveling together") × 保研岛 (Baoyan Dao, "Baoyan Island") — an open-source benchmark for AI agents in Baoyan advising and application planning.
Automatically evaluate your LLMs in Google Colab
Local, OpenAI-compatible text-to-speech (TTS) API using Chatterbox, enabling users to generate voice cloned speech anywhere the OpenAI API is used (e.g. Open WebUI, AnythingLLM, etc.)
Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".
USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
- attention-is-all-you-need
- llm-inference
- llm-training
- pytorch
Fully open-source command-line AI assistant inspired by OpenAI Codex, supporting local language models.
A LLM-based Agent that predict its tasks proactively.