Instructions to use openai/gpt-oss-120b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openai/gpt-oss-120b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="openai/gpt-oss-120b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("openai/gpt-oss-120b")
model = AutoModelForMultimodalLM.from_pretrained("openai/gpt-oss-120b")
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
Local Apps Settings

vLLM

How to use openai/gpt-oss-120b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openai/gpt-oss-120b"
# 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-120b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openai/gpt-oss-120b

SGLang

How to use openai/gpt-oss-120b 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-120b" \
    --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-120b",
		"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-120b" \
        --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-120b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openai/gpt-oss-120b with Docker Model Runner:
```
docker model run hf.co/openai/gpt-oss-120b
```

RuntimeError: expected scalar type Float but found BFloat16 during activation capture

#153

by ojas03 - opened Nov 4, 2025

Discussion

ojas03

Nov 4, 2025

I’m encountering a dtype mismatch error when extracting activations from a model during generation using model.generate(). The error occurs when collecting layer activations for later analysis using NumPy.
I get a warning:
MXFP4 quantization requires Triton and kernels installed: CUDA requires Triton >= 3.4.0, XPU requires Triton >= 3.5.0, we will default to dequantizing the model to bf16
RuntimeError: expected scalar type Float but found BFloat16

This happens while running the following logic:

for layer_name, act in activations.items():
    act_float = act.detach().cpu().to(torch.float32).numpy()
    layer_sums[layer_name].append(act_float)

To reproduce the issue, here’s a minimal snippet:

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]:]))

Followed by activation capture using:

_ = model.generate(**inputs, max_new_tokens=1)
for layer_name, act in activations.items():
    act_float = act.detach().cpu().to(torch.float32).numpy()
    layer_sums[layer_name].append(act_float)

PyTorch version: torch==2.9.0
CUDA version: cuda_12.0.r12.0/compiler.32267302_0
Model: gpt-oss-safeguard-20b
GPU: NVIDIA RTX A6000

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment