Instructions to use Svard/LaViT-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Svard/LaViT-3B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Svard/LaViT-3B")
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("Svard/LaViT-3B")
model = AutoModelForImageTextToText.from_pretrained("Svard/LaViT-3B")
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 Svard/LaViT-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Svard/LaViT-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Svard/LaViT-3B",
		"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/Svard/LaViT-3B

SGLang

How to use Svard/LaViT-3B 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 "Svard/LaViT-3B" \
    --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": "Svard/LaViT-3B",
		"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 "Svard/LaViT-3B" \
        --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": "Svard/LaViT-3B",
		"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 Svard/LaViT-3B with Docker Model Runner:
```
docker model run hf.co/Svard/LaViT-3B
```

Update pipeline tag and add library_name

by nielsr HF Staff - opened Jan 17

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-4

Files changed (1) hide show

README.md +6 -4

README.md CHANGED Viewed

@@ -1,23 +1,25 @@
 ---
-license: apache-2.0
 base_model: Qwen/Qwen2.5-VL-3B-Instruct
 tags:
 - vision-language
 - multimodal
 - reasoning
 - visual-grounding
 - computer-vision
-pipeline_tag: visual-question-answering
 ---
 # LaViT-3B: Aligning Latent Visual Thoughts for Multi-modal Reasoning
-<div align="center">
 **LaViT** is a vision-language model that aligns latent visual thoughts for enhanced multi-modal reasoning.
 [![Paper](https://img.shields.io/badge/Paper-arXiv:2601.10129-b31b1b.svg)](https://arxiv.org/abs/2601.10129)
 [![Model](https://img.shields.io/badge/🤗%20HuggingFace-Model-yellow.svg)](https://huggingface.co/Svard/LaViT-3B)
 </div>
@@ -130,4 +132,4 @@ This model is built upon [Qwen2.5-VL](https://github.com/QwenLM/Qwen3-VL) and in
 - **Paper**: [arXiv:2601.10129](https://arxiv.org/abs/2601.10129)
 - **Code Repository**: [GitHub](https://github.com/Svardfox/LaViT)
-- **Base Model**: [Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct)

 ---
 base_model: Qwen/Qwen2.5-VL-3B-Instruct
+license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: transformers
 tags:
 - vision-language
 - multimodal
 - reasoning
 - visual-grounding
 - computer-vision
 ---
 # LaViT-3B: Aligning Latent Visual Thoughts for Multi-modal Reasoning
+<div align="center\">
 **LaViT** is a vision-language model that aligns latent visual thoughts for enhanced multi-modal reasoning.
 [![Paper](https://img.shields.io/badge/Paper-arXiv:2601.10129-b31b1b.svg)](https://arxiv.org/abs/2601.10129)
 [![Model](https://img.shields.io/badge/🤗%20HuggingFace-Model-yellow.svg)](https://huggingface.co/Svard/LaViT-3B)
+[![GitHub](https://img.shields.io/badge/GitHub-Code-blue?logo=github)](https://github.com/Svardfox/LaViT)
 </div>
 - **Paper**: [arXiv:2601.10129](https://arxiv.org/abs/2601.10129)
 - **Code Repository**: [GitHub](https://github.com/Svardfox/LaViT)
+- **Base Model**: [Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct)