Instructions to use openai/gpt-oss-20b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/gpt-oss-20b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="openai/gpt-oss-20b") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("openai/gpt-oss-20b") model = AutoModelForCausalLM.from_pretrained("openai/gpt-oss-20b", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
- AMD Developer Cloud
- Local Apps Settings
- vLLM
How to use openai/gpt-oss-20b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openai/gpt-oss-20b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openai/gpt-oss-20b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/openai/gpt-oss-20b
- SGLang
How to use openai/gpt-oss-20b with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "openai/gpt-oss-20b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openai/gpt-oss-20b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "openai/gpt-oss-20b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openai/gpt-oss-20b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use openai/gpt-oss-20b with Docker Model Runner:
docker model run hf.co/openai/gpt-oss-20b
This is by far the worst model out there... Won't be using this. ๐ฎ๐๏ธ
Excessive censorship broke the model. It's unusable.
Well as long as you don't want to discuss or get help researching biology, or chemistry, or math, or coding, or work with large data sets, or do creative writing, or have a simple conversation without the AI seeming like it feels like Sam Altman is standing behind it with one of those old car cigarette lighters ready to punish it if it says anything he doesn't like.... then it's great.
You don't exactly need to be very controversial when talking to this bot to get shut down. I've gotten tons of baffling shutdowns, everything from claiming that I'm hurting children because university students are fighting to just reacting ill to cursing (though it only happened to me well into a chat, seems fine with cursing in the start). I haven't ever had a teacher or even a priest that has ever been this uppedy with me.
Already deleted this one, a waste of space.