gpt-oss-20b

There are 40 repositories under gpt-oss-20b topic.

  • oumi

    Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!

    Language:Python8.5k

  • models-ai-local-docker

    En este repositorio encontraras de una forma centralizada y facil, para poder correr alguno de tus modelos favortios localmente usando docker

    Language:Shell15

  • FREISA

    Four-legged Robot Ensuring Intelligent Sprinkler Automation

    Language:Jupyter Notebook14

  • gguf-loader

    Run ChatGPT OSS, Groke 2 Locally — GGUF Loader for 120B/20B Models | Open Source & Offline

    Language:Python11

  • GPT-OSS-MoE-ExpertFingerprinting

    ExpertFingerprinting: Behavioral Pattern Analysis and Specialization Mapping of Experts in GPT-OSS-20B's Mixture-of-Experts Architecture

    Language:HTML10

  • gptoss-proxy

    Unlimited gpt-oss api openai compatible

    Language:JavaScript8

  • agentsculptor

    agentsculptor is an experimental AI-powered development agent designed to analyze, refactor, and extend Python projects automatically. It uses an OpenAI-like planner–executor loop on top of a vLLM backend, combining project context analysis, structured tool calls, and iterative refinement. It has only been tested with gpt-oss-120b via vLLM.

    Language:Python6

  • deploy-gpt-oss-in-ec2

    Local deployment of gpt-oss-20b model in AWS EC2 instance.

    Language:Python4

  • awesome-gpt-oss

    A curated list of awesome GPT-OSS resources, tools, tutorials, and projects

    2

  • MCP-demo

    MCP with GPT-OSS

    Language:Python2

  • load-test-vllm-gpt-oss-20b

    Load testing openai/gpt-oss-20b with vLLM and Docker

    Language:Python1

  • secure-research-assistant

    Secure offline research assistant

    Language:Python1

  • GPT-OSS-20B-Windows-16GB-RTX4090

    No Hopper architecture (RTX 5090, etc.) required! <16 GB VRAM, Windows.

    Language:Python1

  • ai-eng-course-project

    AI Agent-Based Nutrition Advisor

    Language:Python1

  • gpt-oss

    FastAPI OSS LLM Gateway — OpenAI-compatible API for local backends (Ollama, vLLM, LM Studio) with file-aware prompts.

    Language:Python1
  • app

    app

    Sustainability + AI = Tasty food :P Recignize allows you to use your existing utensils, veggies, fruits, etc., to find the best recipes using the power of multimodal LLMs.

    Language:TypeScript1

  • red-teaming

    A sophisticated red-teaming agent built with LangGraph and Ollama to probe OpenAI's GPT-OSS-20B model for vulnerabilities and harmful behaviors. (Specifically built for the OpenAI Open Model Hackathon)

    Language:Python

  • LearnSynth

    Turn text/audio/video into study packs (summaries, concept maps, quizzes). Flutter + FastAPI. Uses GPT-OSS-20B (Replicate) by default, with optional fallbacks (OpenAI/Anthropic) and OSS modes (Ollama/vLLM).

    Language:Dart

  • ai-humanity-passport

    An AI that scans GitHub repos and issues a badge of honor to projects that benefit humanity. Our submission for the OpenAI Open Model Hackathon ("For Humanity" category). Hackathon Link - https://devpost.com/software/humanity-passport

    Language:TypeScript

  • DecoPilot

    Dự án MVP “Interior Design Agent” – trợ lý AI tư vấn thiết kế phòng làm việc dựa trên Mastra (Agent + RAG), LLM gpt-oss, embedding bge-m3 và vector store Chroma.

    Language:TypeScript

  • instacheck

    InstaCheck is a Chrome extension that helps users verify the authenticity of claims in Instagram Reels in real time.

    Language:Python

  • gpt-oss-simplechat

    A tiny .NET console app that let's you chat with a local gpt-oss-20b AI model.

    Language:C#

  • cognitive_reframer

    Cognitive Reframer — Private, offline AI tool that helps you transform negative thoughts into positive, actionable perspectives, powered by local gpt-oss reasoning.

    Language:Python

  • sql-where-clause-extraction-from-user-query

    "SQL Where Clause" Extraction from User Chat Query with LLM

    Language:Python

  • gpt-oss-20b-FineTuning

    Fine-tuning workflow for an open-source LLM (20B-class) using LoRA with Hugging Face Transformers + TRL.

    Language:Jupyter Notebook

  • NPC-Chatbot

    A chatbot designed with C++ SFML and Python Flask using Open AI gpt-oss-20b to give non player characters advanced dialogue options.

    Language:C++

  • gpt-oss-gradio-chat

    A Gradio chat interface for gpt-oss models that uses either the OpenAI or Groq API

    Language:Python

  • data-analyst-mcp-app

    🔌 Bridge between Ollama and MCP tools. Lets your LLM call real tools (read files, analyze CSVs, edit text) in response to natural language queries.

    Language:Python

  • cot_mirage

    Teaching LLMs to follow steps off a cliff

    Language:Python

  • gptoss-redteam-pack

    Reproducible red-team findings for openai/gpt-oss-20b: five minimal harnesses with checks, zips & manifest (v0.9.3).

    Language:HTML

  • Supervised-Fine-Tuning-of-GPT-OSS-20B-on-OpenAI-s-gsm8k-reasoning-with-LoRA

    In this we finetune GPT-OSS-20B on OpenAI's gsm8k dataset

    Language:Jupyter Notebook

  • ai-agents-mcp-docker

    AI-powered GitHub repository assistant using Model-Context-Protocol (MCP). Features a local agent that queries GitHub APIs through a Dockerized MCP Gateway, delivering intelligent, context-aware answers about any repository.

    Language:Python

  • gpt-oss-rt-run

    Kaggle Red‑Teaming Challenge: OpenAI gpt-oss-20b

    Language:Python

  • gpt-oss_agentic_robot

    gpt-oss 20b powered agentic 6-DoF cleaning robot

    Language:Python

  • Takon-ask-your-data

    TAKON is a RAG-based Q&A app that lets you interact with your own documents using GPT-OSS-20B. Built with Streamlit for an intuitive browser interface.

    Language:Python

  • fine-tunning

    This is a Korean language fine-tuning project for GPT-OSS 20B model using Unsloth framework. The project focuses on educational content generation in Korean using LoRA (Low-Rank Adaptation) techniques for efficient training.

    Language:Python