Instructions to use wealthcoders/gpt-oss-20b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wealthcoders/gpt-oss-20b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="wealthcoders/gpt-oss-20b") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("wealthcoders/gpt-oss-20b") model = AutoModelForCausalLM.from_pretrained("wealthcoders/gpt-oss-20b") 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]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use wealthcoders/gpt-oss-20b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "wealthcoders/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": "wealthcoders/gpt-oss-20b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/wealthcoders/gpt-oss-20b
- SGLang
How to use wealthcoders/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 "wealthcoders/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": "wealthcoders/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 "wealthcoders/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": "wealthcoders/gpt-oss-20b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use wealthcoders/gpt-oss-20b with Docker Model Runner:
docker model run hf.co/wealthcoders/gpt-oss-20b
Commit History
Update requirements.txt d7a1433 verified
Update requirements.txt 2390554 verified
Update requirements.txt bcb8edf verified
Update requirements.txt 954fbe9 verified
Update requirements.txt ecbfa5e verified
Update requirements.txt 9953ea9 verified
Update requirements.txt 916ac1c verified
add requirements.txt df5dec9
Konstantin commited on
copied files 68ee47a
Konstantin commited on
copied files 9a2d7d0
Konstantin commited on