nllg
/

Model Card for DeTikZify-DS7b

DeTikZify-DS1.3b is a language model that automatically converts sketches and existing scientific figures into editable, semantics-preserving TikZ graphics programs. It is based on DeepSeek Coder 7b v1.5 and was fine-tuned on DaTikZv2. Check out the DeTikZify project for more information and tips on how to best run the model.

Usage

from operator import itemgetter

from detikzify.model import load
from detikzify.infer import DetikzifyPipeline

image = "https://w.wiki/A7Cc"
pipeline = DetikzifyPipeline(*load(
    model_name_or_path="nllg/detikzify-ds-7b",
    device_map="auto",
    torch_dtype="bfloat16",
))

# generate a single TikZ program
fig = pipeline.sample(image=image)

# if it compiles, rasterize it and show it
if fig.is_rasterizable:
    fig.rasterize().show()

# run MCTS for 10 minutes and generate multiple TikZ programs
figs = set()
for score, fig in pipeline.simulate(image=image, timeout=600):
    figs.add((score, fig))

# save the best TikZ program
best = sorted(figs, key=itemgetter(0))[-1][1]
best.save("fig.tex")
Downloads last month
103
Safetensors
Model size
6.92B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train nllg/detikzify-ds-7b

Collection including nllg/detikzify-ds-7b