ai models

13 bookmarks in this category

• GPT-OSS 120B on HuggingFace

  HuggingFace • Aug 5, 2025

  117B parameter model with extreme sparsity for production use

  [gpt-oss] [llm] [apache-2.0]

• GPT-OSS 20B on HuggingFace

  HuggingFace • Aug 5, 2025

  21B parameter model optimized for local deployment

  [gpt-oss] [llm] [apache-2.0] [local]

• Introducing GPT-OSS

  OpenAI • Aug 5, 2025

  Detailed announcement of GPT-OSS models with benchmarks and examples

  [gpt-oss] [blog] [announcement]

• GPT-OSS GitHub Repository

  GitHub • Aug 5, 2025

  Reference PyTorch implementation and tools for GPT-OSS models

  [gpt-oss] [pytorch] [implementation]

• OpenAI Harmony

  GitHub • Aug 5, 2025

  Structured response format specification for reasoning and tool use

  [harmony] [gpt-oss] [response-format]

• GPT-OSS Model Card

  OpenAI • Aug 5, 2025

  Technical specifications and training details for GPT-OSS models

  [gpt-oss] [model-card] [specifications]
  resources:

  ↓ Local PDF Copy

• Run GPT-OSS with Ollama

  OpenAI Cookbook • Aug 5, 2025

  Guide for running GPT-OSS models locally using Ollama

  [gpt-oss] [ollama] [local-deployment]

• OpenAI Open Models

  OpenAI • Aug 5, 2025

  Official announcement page for GPT-OSS open-weight reasoning models

  [gpt-oss] [openai] [announcement]

• GPT-OSS Playground

  OpenAI • Aug 5, 2025

  Interactive demo to try GPT-OSS models directly in browser

  [gpt-oss] [demo] [playground]

• GPT-OSS Red Teaming Challenge

  Kaggle • Aug 5, 2025

  $500k Kaggle competition for community safety testing

  [gpt-oss] [red-teaming] [kaggle] [competition]

• GPT-OSS Model Safety Paper

  OpenAI • Aug 5, 2025

  Comprehensive safety analysis including malicious fine-tuning testing

  [gpt-oss] [safety] [research]
  resources:

  ↓ Local PDF Copy

• Run GPT-OSS with Transformers

  OpenAI Cookbook • Aug 5, 2025

  Development setup guide using HuggingFace Transformers library

  [gpt-oss] [transformers] [huggingface]

• Run GPT-OSS with vLLM

  OpenAI Cookbook • Aug 5, 2025

  Production deployment guide using vLLM for high-performance inference

  [gpt-oss] [vllm] [production]