Mod
50 items across the graph — tagged with Mod.
From the graph · 50
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference a…
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
Build AI Agents, Visually
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, Op…
Build and run agents you can see, understand and trust.
The Modular Platform (includes MAX & Mojo)
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with exp…
The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connect…
ModelScope: bring the notion of Model-as-a-Service to life.
Web dashboard for Hermes Agent — multi-platform AI chat, session management, scheduled jobs, usage analytics
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causa…
⚙️🦀 Build modular and scalable LLM Applications in Rust
⚡ TabPFN: Foundation Model for Tabular Data ⚡
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets…
Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline…
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
Hugging Face model with 6436 likes. Tags: text-to-speech, en, arxiv:2306.07691, arxiv:2203.02395, base_model:yl4579/StyleTTS2-LJSpeech, base_model:finetune:yl45…
The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no down…
Chronos: Pretrained Models for Time Series Forecasting
OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density
Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
Build local voice agents with open-source models
Hugging Face model with 4701 likes. Tags: vllm, safetensors, mixtral, fr, it, de, es, en, base_model:mistralai/Mixtral-8x7B-v0.1, base_model:finetune:mistralai/…
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
Optimizing inference proxy for LLMs
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed perf…
【三年面试五年模拟】AIGC/LLM/AI Agent算法工程师面试秘籍。涵盖AIGC、LLM大模型、AI Agent、传统深度学习、自动驾驶、机器学习、计算机视觉、自然语言处理、强化学习、大数据挖掘、具身智能、元宇宙、AGI等AI行业面试笔试干货经验与核心知识。
TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series tr…
The Unofficial and Awesome Home Assistant MCP Server
The official Python client for the Hugging Face Hub.
Achieve state of the art inference performance with modern accelerators on Kubernetes
The most accurate document search and store for building AI apps
Hugging Face model with 3624 likes. Tags: transformers, pytorch, multi_modality, muiltimodal, text-to-image, unified-model, any-to-any, arxiv:2501.17811, licens…
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
Hugging Face model with 3119 likes. Tags: transformers, safetensors, gemma4, image-text-to-text, conversational, base_model:google/gemma-4-31B, base_model:finet…
Hugging Face model with 2937 likes. Tags: transformers, safetensors, qwen2, text-generation, chat, conversational, en, arxiv:2309.00071, arxiv:2412.15115, base_…
Hugging Face model with 2884 likes. Tags: safetensors, model_hub_mixin, pytorch_model_hub_mixin, text-to-speech, en, arxiv:2305.09636, license:apache-2.0, regio…
🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Sv…
🔥 Java enterprise application development framework for full scenario: Restrained, Efficient, Open, Ecologicalll!!! 700% higher concurrency 50% memory savings…
Hugging Face model with 2659 likes. Tags: vllm, safetensors, mistral, mistral-common, base_model:mistralai/Mistral-7B-v0.3, base_model:finetune:mistralai/Mistra…
The Self-Coding System for Your App — Alan AI SDK for Web
A simple, performant, and scalable Jax LLM!
Community maintained hardware plugin for vLLM on Ascend
VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。
🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.