Stars
Lightweight offline Linux command tutor using a local LLM and ChromaDB.
Codebase for Berkeley Humanoid Lite
Integrate cutting-edge LLM technology quickly and easily into your apps
Use your favorite LLM to provide a chat interface with any youtube video you choose.
LostRuins / koboldcpp
Forked from ggml-org/llama.cppRun GGUF models easily with a KoboldAI UI. One File. Zero Install.
Insurance AI Assistant A smart system combining PostgreSQL, Milvus, and specialized AI agents (Life/Home/Auto) to answer insurance queries accurately. Features real-time sync, semantic search via O…
Memory for AI Agents; SOTA in AI Agent Memory, beating OpenAI Memory in accuracy by 26% - https://mem0.ai/research
Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.
The simplest, fastest repository for training/finetuning small-sized VLMs.
Towards Understanding the Mixture-of-Experts Layer in Deep Learning
A curated reading list of research in Mixture-of-Experts(MoE).
A web application for creating and managing Databricks cluster policies with an interactive UI, allowing users to configure policy attributes, inherit from policy families, and manage policy defini…
Seamlessly integrate state-of-the-art transformer models into robotics stacks
ROSA 🤖 is an AI Agent designed to interact with ROS1- and ROS2-based robotics systems using natural language queries. ROSA helps robot developers inspect, diagnose, understand, and operate robots.
LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath
Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them
OpenChat: Advancing Open-source Language Models with Imperfect Data
✨ Kubectl plugin to create manifests with LLMs
Apache Polaris, the interoperable, open source catalog for Apache Iceberg
DeepSeek Native Sparse Attention pytorch implementation
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
Fivetran data models for Facebook Ads built using dbt.
Curated list of datasets and tools for post-training.
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.