GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Caffin
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Caffin
Model Tree
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Input Modalities
Output Modalities
Supported Functionality
This model is intended for:
Generated SVG should be reviewed and sanitized before being rendered in production web pages or downstream applications.
bash
pip install "transformers>=4.51.0" torch accelerate safetensorspython
import reimport torchfrom 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"` block before rendering. ## Model Notes SVGThinker is trained directly in SVG code space. The paper describes a sequentialannotation pipeline that aligns natural-language descriptions with the step-by-stepconstruction 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 ```bibtex@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}}pip install "transformers>=4.51.0" torch accelerate safetensorsimport reimport torchfrom 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"` block before rendering. ## Model Notes SVGThinker is trained directly in SVG code space. The paper describes a sequentialannotation pipeline that aligns natural-language descriptions with the step-by-stepconstruction 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 ```bibtex@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}}