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

Libraries

How to use mjf-su/AutoVLA with Transformers:

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

pipe = pipeline("image-text-to-text", model="mjf-su/AutoVLA")
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/AutoVLA")
model = AutoModelForMultimodalLM.from_pretrained("mjf-su/AutoVLA")
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/AutoVLA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mjf-su/AutoVLA"
# 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/AutoVLA",
		"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/AutoVLA

SGLang

How to use mjf-su/AutoVLA 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/AutoVLA" \
    --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/AutoVLA",
		"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/AutoVLA" \
        --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/AutoVLA",
		"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/AutoVLA with Docker Model Runner:
```
docker model run hf.co/mjf-su/AutoVLA
```

AutoVLA / training_config.json

mjf-su

Add files using upload-large-folder tool

1aebaf7 verified about 1 month ago

Raw

History Blame Contribute Delete

1.81 kB

	{
	"checkpoint": "/workspace/fms4navigation/models/checkpoint-1832",
	"jsonl": "/workspace/fms4navigation/datasets/AutoVLA/CounterfactualVLA-train.jsonl",
	"data_root": "/workspace/fms4navigation/datasets/AutoVLA/camera/camera_front_wide_120fov",
	"eval_jsonl": "/workspace/fms4navigation/datasets/AutoVLA/CounterfactualVLA-val.jsonl",
	"mode": "adaptive",
	"config_path": "/workspace/fms4navigation/configs/prompt/CounterfactualVLA.yaml",
	"chat_template_path": null,
	"output_dir": "/workspace/fms4navigation/results/AutoVLA-sft",
	"num_epochs": 1,
	"max_steps": -1,
	"per_device_train_batch_size": 16,
	"per_device_eval_batch_size": null,
	"gradient_accumulation_steps": 3,
	"learning_rate": 1e-06,
	"warmup_ratio": 0.03,
	"lr_scheduler_type": "constant",
	"completion_only_loss": true,
	"bf16": true,
	"fp16": false,
	"flash_attn": false,
	"gradient_checkpointing": true,
	"seed": 42,
	"only_complete": true,
	"ade_threshold": 9.1189,
	"ade_field": null,
	"eval_n": 500,
	"reaction_seconds": 2.0,
	"prediction_horizon": 6.0,
	"past_trajectory_step_sec": 0.25,
	"fut_trajectory_step_sec": 0.25,
	"save_steps": 500,
	"save_total_limit": 3,
	"save_milestones": 0,
	"resume_from_checkpoint": false,
	"save_model": true,
	"eval_steps": null,
	"use_lora": false,
	"lora_r": 16,
	"lora_alpha": 32,
	"lora_dropout": 0.05,
	"wandb_project": "matt-router",
	"run_name": "AutoVLA",
	"login_to_wandb": true,
	"logging_steps": 10,
	"activation_eval_n": 128,
	"activation_eval_steps": null,
	"hf_repo": null,
	"hf_token": null,
	"hf_private": false,
	"dataloader_num_workers": 4,
	"n_hard_train": 99982,
	"n_easy_train": 100000,
	"hard_fraction_train": 0.4999549959496355,
	"n_hard_val": 250,
	"n_easy_val": 250,
	"timestamp_utc": "2026-05-19T13:03:22.968442Z"
	}