Instructions to use Caffin/SVGThinker-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Caffin/SVGThinker-7B with Transformers:

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

pipe = pipeline("text-generation", model="Caffin/SVGThinker-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Caffin/SVGThinker-7B")
model = AutoModelForCausalLM.from_pretrained("Caffin/SVGThinker-7B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Caffin/SVGThinker-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Caffin/SVGThinker-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Caffin/SVGThinker-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Caffin/SVGThinker-7B

SGLang

How to use Caffin/SVGThinker-7B 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 "Caffin/SVGThinker-7B" \
    --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": "Caffin/SVGThinker-7B",
		"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 "Caffin/SVGThinker-7B" \
        --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": "Caffin/SVGThinker-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Caffin/SVGThinker-7B with Docker Model Runner:
```
docker model run hf.co/Caffin/SVGThinker-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

SVGThinker-7B

SVGThinker-7B is a text-to-SVG generation model introduced in SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation. It generates editable SVG code from natural-language descriptions, with a focus on compact icon-style vector graphics.

The model is fine-tuned from deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and is released as BF16 sharded safetensors.

Intended Use

This model is intended for:

generating SVG icons from English text prompts
prototyping simple vector graphics
producing editable SVG markup rather than raster images
research on text-to-SVG and structured code generation

Generated SVG should be reviewed and sanitized before being rendered in production web pages or downstream applications.

Quick Start

pip install "transformers>=4.51.0" torch accelerate safetensors

import re
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Caffin/SVGThinker-7B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    use_safetensors=True,
)

description = "A minimalist calendar icon with two black tabs and a bold checkmark below it."
prompt = "Review the given information below and generate a svg according to it.\n" + description

messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
).to(model.device)

with torch.no_grad():
    output = model.generate(
        inputs,
        max_new_tokens=4096,
        do_sample=True,
        temperature=0.8,
        top_p=0.6,
        repetition_penalty=1.05,
    )

text = tokenizer.decode(output[0], skip_special_tokens=False)
match = re.search(r"<svg.*?</svg>", text, flags=re.DOTALL)
print(match.group(0) if match else text)

The model may emit reasoning text before the final SVG. For most applications, extract the <svg>...</svg> block before rendering.

Model Notes

SVGThinker is trained directly in SVG code space. The paper describes a sequential annotation pipeline that aligns natural-language descriptions with the step-by-step construction of SVG primitives, helping the model generate more editable SVG code.

For full training data, annotation, and evaluation details, see the paper.

Evaluation Snapshot

On the paper's 1,000 held-out text-to-SVG prompts, SVGThinker reports:

Model	FID lower is better	CLIP higher is better	FID-CLIP lower is better	Primitive support
SVGThinker-7B	34.06	0.2765	21.08	all

Limitations

Outputs may be malformed, incomplete, or visually inconsistent with the prompt.
The model is best suited for simple to moderately complex icon-style graphics.
It may struggle with photorealistic scenes, dense layouts, and text-heavy SVGs.
SVG is executable markup in browser contexts; treat generated SVG as untrusted.
The model primarily targets English prompts.

Citation

@inproceedings{chen2025svgthinker,
  title = {SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation},
  author = {Chen, Hanqi and Zhao, Zhongyin and Chen, Ye and Liang, Zhujin and Ni, Bingbing},
  booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia},
  year = {2025},
  publisher = {ACM},
  doi = {10.1145/3746027.3755392},
  url = {https://arxiv.org/abs/2509.24299}
}

Downloads last month: 7

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Caffin/SVGThinker-7B

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Finetuned

(314)

this model

Quantizations

1 model

Space using Caffin/SVGThinker-7B 1

Paper for Caffin/SVGThinker-7B

SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation

Paper • 2509.24299 • Published Sep 29, 2025 • 1

Caffin
/

SVGThinker-7B