XiaomingX
Follow
Lists (2)
Stars
GLM-4 series: Open Multilingual Multimodal Chat LMs | εΌζΊε€θ―θ¨ε€ζ¨‘ζε―Ήθ―樑ε
Training Large Language Model to Reason in a Continuous Latent Space
π Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash attention v2.
ππ€ Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper
Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. Cβ¦
Fast and extensible multi-platform HTTP/1-2-3 web server with automatic HTTPS
PyTorch per step fault tolerance (actively under development)
cmaclell / py_rete
Forked from GNaive/naive-retePython RETE algorithm
Real time transcription with OpenAI Whisper.
Model Context Protocol Servers
The official Node.js / Typescript library for the Google Gemini API
Make websites accessible for AI agents
Whisper realtime streaming for long speech-to-text transcription and translation
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
Generative Models by Stability AI
Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.
Drag & drop UI to build your customized LLM flow
From RAG chatbots to code assistants to complex agentic pipelines and beyond, build LLM systems that run better, faster, and cheaper with tracing, evaluations, and dashboards.
Documentation for Google's Gen AI site - including the Gemini API and Gemma
The official Python library for the Google Gemini API
Langflow is a low-code app builder for RAG and multi-agent AI applications. Itβs Python-based and agnostic to any model, API, or database.
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Examples and guides for using the Gemini API
Bring data to life with SVG, Canvas and HTML. πππ
Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.