Instructions to use nota-ai/phiva-4b-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nota-ai/phiva-4b-hf with Transformers:

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

pipe = pipeline("image-text-to-text", model="nota-ai/phiva-4b-hf")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("nota-ai/phiva-4b-hf")
model = AutoModelForImageTextToText.from_pretrained("nota-ai/phiva-4b-hf")
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

vLLM

How to use nota-ai/phiva-4b-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nota-ai/phiva-4b-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nota-ai/phiva-4b-hf",
		"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/nota-ai/phiva-4b-hf

SGLang

How to use nota-ai/phiva-4b-hf 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 "nota-ai/phiva-4b-hf" \
    --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": "nota-ai/phiva-4b-hf",
		"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 "nota-ai/phiva-4b-hf" \
        --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": "nota-ai/phiva-4b-hf",
		"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 nota-ai/phiva-4b-hf with Docker Model Runner:
```
docker model run hf.co/nota-ai/phiva-4b-hf
```

Usage

import requests
from PIL import Image

import torch
from transformers import AutoProcessor, LlavaForConditionalGeneration

model_id = "nota-ai/phiva-4b-hf"

prompt = "USER: <image>\nWhat are these?\nASSISTANT:"
image_file = "http://images.cocodataset.org/val2017/000000039769.jpg"

model = LlavaForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True, 
    attn_implementation="eager"
).to(0)

processor = AutoProcessor.from_pretrained(model_id)


raw_image = Image.open(requests.get(image_file, stream=True).raw)
inputs = processor(prompt, raw_image, return_tensors='pt').to(0, torch.float16)

output = model.generate(**inputs, max_new_tokens=200, do_sample=False)
print(processor.decode(output[0][inputs['input_ids'].shape[-1]:], skip_special_tokens=True))

Terms of use

The vision-language model published in this repository was developed by combining several modules (e.g., vision encoder, language model). Commercial use of any modifications, additions, or newly trained parameters made to combine these modules is not allowed. However, commercial use of the unmodified modules is allowed under their respective licenses. If you wish to use the individual modules commercially, you may refer to their original repositories and licenses provided below.

Vision encoder (license) link : Model, License

Language model (license) link : Model, License

VLM framework (license) link: Github, License

Downloads last month: 44

Safetensors

Model size

4B params

Tensor type

F16

Datasets used to train nota-ai/phiva-4b-hf

Collection including nota-ai/phiva-4b-hf

Efficient Large Vision-Language Model

Collection

ERGO: LVLM trained with RL on efficiency objectives; https://github.com/nota-github/ERGO • 3 items • Updated Feb 22 • 25