OneComp
Fujitsu Research's post-training quantization pipeline for LLMs (QEP, AutoBit, JointQ, rotation) with vLLM plugin (arXiv:2603.28845).
Fujitsu Research's post-training quantization pipeline for LLMs (QEP, AutoBit, JointQ, rotation) with vLLM plugin (arXiv:2603.28845).
Alpaca-LoRA as Chatbot service
An efficient VLA model leveraging State Space Models (Mamba) instead of standard self-attention, offering linear inference complexity for efficient, recurrent robotic reasoning.
A 7B-parameter open-source Vision-Language-Action model trained on 970K+ robot demonstrations from the Open X-Embodiment dataset for generalist robotic manipulation.
Open-source VLA models from Physical Intelligence, including π₀ and π₀.5 — flow-based vision-language-action models pretrained on large-scale robot data with fine-tuning support.
A transformer-based generalist robot policy pretrained on 800K+ robot trajectories from the Open X-Embodiment dataset. Supports language instructions, goal images, and fine-tuning to new embodiments.
A central community library by Hugging Face for AI in robotics — end-to-end learning tools, data pipelines, and support for training/deploying VLA models.
A continuous diffusion-based Vision-Language-Action model that integrates diffusion policies into autoregressive VLMs for robust and precise continuous robotic control.
Bark is a transformer-based text-to-audio model created by Suno. Bark can generate highly realistic, multilingual speech as well as other audio - including music, background noise and simple sound effects.
A latent text-to-image diffusion model
produces high quality object masks from input prompts such as points or boxes, and it can be used to generate masks for all objects in an image.
A frankensteinian amalgamation of notebooks, models and techniques for the generation of AI Art and Animations.
StableLM: Stability AI Language Models
A Chinese LLM, Based on LLaMA and fine tune by Stanford Alpaca, Alpaca LoRA, Japanese-Alpaca-LoRA.
An Open Bilingual Pre-Trained Model (ICLR 2023)
ChatGLM2-6B is the second-generation version of the open-source bilingual (Chinese-English) chat model ChatGLM-6B.
An Open Bilingual Pre-Trained Model, quantization of ChatGLM-130B, can run on consumer-level GPUs.
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
BigScience Large Open-science Open-access Multilingual Language Model
A 7B Large Language Model fine-tune by 34B Chinese Character Corpus, based on LLaMA and Alpaca.
Code and documentation to train Stanford's Alpaca models, and generate the data.
Deploy multi-agent workflows as APIs.
Memory-efficient FastText variant with exact trie n-gram IDs, structure-aware row sharing, and mmap serving for large-vocabulary NLP.
Community based data collection, packed in gem. Get list of pretty much anything (stop words, countries, non words) in txt, JSON or hash. Demo/Search for a list
[Deprecated]
A data management tool for humans. [Deprecated]
Code for Kaggle Dogs vs. Cats competition.
Topic Modelling the Sarah Palin emails.
> A Modular Framework for Multi-Modal Tabular Learning.
A PyTorch implementation of Justin Johnson's neural-style (neural style transfer).
Scripts to load several popular datasets including
Straight forward plotting built on D3. [Deprecated]
A solution for hosting MCP Servers by extending the API Gateway (based on Envoy) with wasm plugins.
MCP server to create, read, update, and delete Zoom meetings via the Zoom API.
MCP server to extract YouTube video metadata with proxy support.
MCP server to interact with the Solana blockchain using the Solana Agent Kit, supporting 40+ protocol actions.
MCP server to send emails using Resend services.
MCP server to run Python code securely in a sandbox environment via MCP calls, powered by Deno and Pyodide.
MCP server connecting to Microsoft OneNote via Microsoft Graph API; read and create notebooks, sections, and pages.
MCP server to connect and manage SaaS tools like HubSpot and Salesforce.
MCP server for converting various file formats into Markdown.
MCP server for converting documents between formats using Pandoc.
MCP server for interacting with any JDBC-compatible database. Supports query, insert, update, delete operations on MySQL, PostgreSQL, Oracle, SQL Server, SQLite, and more.
MCP server to run more than 200 on-chain actions on any blockchain including Ethereum, Solana, and Base.
MCP server for the Edwin SDK, enabling AI agents to interact with DeFi protocols across EVM, Solana, and other blockchains.
MCP server implementation for Discord API integration by Klavis AI.
A GraphRAG memory server with customizable ingestion, data processing, and search capabilities.
MCP server that enables web search using Baidu Cloud's AI search.