openai gpt-oss: gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
We released the models with native quantization support. Apply_patch can be used to create, update or delete files locally. As a result the PythonTool defines its frostybet own tool description to override the definition in openai-harmony. During the training the model used a stateful tool which makes running tools between CoT loops easier. The model […]