Instructions to use mjf-su/PhysicalAI-base-VLA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mjf-su/PhysicalAI-base-VLA with Transformers:

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

pipe = pipeline("image-text-to-text", model="mjf-su/PhysicalAI-base-VLA")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("mjf-su/PhysicalAI-base-VLA")
model = AutoModelForMultimodalLM.from_pretrained("mjf-su/PhysicalAI-base-VLA")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mjf-su/PhysicalAI-base-VLA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mjf-su/PhysicalAI-base-VLA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mjf-su/PhysicalAI-base-VLA",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/mjf-su/PhysicalAI-base-VLA

SGLang

How to use mjf-su/PhysicalAI-base-VLA 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 "mjf-su/PhysicalAI-base-VLA" \
    --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": "mjf-su/PhysicalAI-base-VLA",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "mjf-su/PhysicalAI-base-VLA" \
        --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": "mjf-su/PhysicalAI-base-VLA",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use mjf-su/PhysicalAI-base-VLA with Docker Model Runner:
```
docker model run hf.co/mjf-su/PhysicalAI-base-VLA
```

PhysicalAI-base-VLA / README.md

mjf-su

Fix README.md

bd580dd verified 3 months ago

preview code

Raw

History Blame Contribute Delete

4.01 kB

	---
	base_model: Qwen/Qwen3-VL-4B-Thinking
	library_name: transformers
	model_name: PhysicalAI-reason-VLA
	tags:
	- generated_from_trainer
	- sft
	- trl
	- vision-language
	- autonomous-driving
	- reasoning
	license: mit
	datasets:
	- mjf-su/PhysicalAI-reason-US
	---

	# PhysicalAI-reason-VLA

	A vision-language driving policy fine-tuned from [mjf-su/PhysicalAI-base-VLA](https://huggingface.co/mjf-su/PhysicalAI-base-VLA) (itself based on [Qwen/Qwen3-VL-4B-Thinking](https://huggingface.co/Qwen/Qwen3-VL-4B-Thinking)) using supervised fine-tuning with [TRL](https://github.com/huggingface/trl).

	This model extends the base waypoint-prediction VLA with structured chain-of-thought reasoning and discrete driving decisions, trained on 10k Gemini-annotated driving scenes for 2 epochs.

	---

	## Input / Output

	Inputs
	- A forward-facing camera image
	- Past ego-vehicle waypoints in the vehicle's relative frame

	Output

	```
	<think>
	{
	"scene": "2–3 sentence static scene description",
	"move_justification": "2–3 sentence causal explanation linking scene to decisions",
	}
	</think>
	<action>
	<longitudinal_token><lateral_token>
	</action>
	<wp>[x.xx,y.yy,t.tttt]</wp>
	<wp>[x.xx,y.yy,t.tttt]</wp>
	...
	```

	The model produces three outputs in sequence: a reasoning trace (`<think>`), discrete longitudinal and lateral driving decisions (`<action>`), and future trajectory waypoints (`<wp>`).

	---

	## Decision Tokens

	Each `<action>` block contains exactly one longitudinal and one lateral token.

	Longitudinal — `<stop>` · `<yield>` · `<follow>` · `<gap_search>` · `<pass>` · `<adapt>` · `<cruise>`

	Lateral — `<turn_left>` · `<turn_right>` · `<lc_left>` · `<lc_right>` · `<merge>` · `<nudge_out_left>` · `<nudge_out_right>` · `<nudge_in_left>` · `<nudge_in_right>` · `<pull_over>` · `<abort>` · `<lane_keep>`

	These are registered as genuine single tokens in the vocabulary (not subword decompositions), enabling efficient probability measurement over the full decision space with a single forward pass.

	---

	## Training

	\| \| \|
	\|---\|---\|
	\| Base model \| [mjf-su/PhysicalAI-base-VLA](https://huggingface.co/mjf-su/PhysicalAI-base-VLA) \|
	\| Dataset \| [mjf-su/PhysicalAI-reason-US](https://huggingface.co/datasets/mjf-su/PhysicalAI-reason-US) \|
	\| Annotation \| Gemini batch API (chain-of-thought labels on real US driving data) \|
	\| Samples \| 10,000 \|
	\| Epochs \| 2 \|
	\| Method \| Completion-only SFT via TRL \|

	---

	## Quick Start

	```python
	from transformers import AutoProcessor, AutoModelForImageTextToText
	from PIL import Image

	model_id = "mjf-su/PhysicalAI-reason-VLA"
	processor = AutoProcessor.from_pretrained(model_id)
	model = AutoModelForImageTextToText.from_pretrained(model_id, device_map="auto")

	image = Image.open("forward_camera.jpg")

	past_waypoints = "<wp>[0.00,0.00,0.0000]</wp>\n<wp>[0.51,0.00,0.0001]</wp>\n..."

	messages = [
	{
	"role": "system",
	"content": [{"type": "text", "text": "You are a helpful AI assistant ..."}]
	},
	{
	"role": "user",
	"content": [
	{"type": "image"},
	{"type": "text", "text": f"[PAST-VEHICLE-MOTION]:\n{past_waypoints}"}
	]
	}
	]

	prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
	inputs = processor(text=[prompt], images=[image], return_tensors="pt").to(model.device)
	outputs = model.generate(**inputs, max_new_tokens=512)
	print(processor.batch_decode(outputs, skip_special_tokens=True)[0])
	```

	---

	## Citation

	```bibtex
	@misc{vonwerra2022trl,
	title = {{TRL: Transformer Reinforcement Learning}},
	author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching
	and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul
	and Quentin Gallou{\'e}dec},
	year = 2022,
	journal = {GitHub repository},
	publisher = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
	}
	```