---
license: llama2
datasets:
- nllg/datikz-v2
---
# Model Card for DeTi*k*Zify-CL7b
DeTi*k*Zify-CL7b is a language model that automatically converts
sketches and existing scientific figures into editable, semantics-preserving
Ti*k*Z graphics programs. It is based on [CodeLlama
7b](https://huggingface.co/meta-llama/CodeLlama-7b-hf) and was fine-tuned on
[DaTi*k*Zv2](https://huggingface.co/datasets/nllg/datikz-v2). Check
out the [DeTi*k*Zify](https://github.com/potamides/DeTikZify) project for more
information and tips on how to best run the model.
## Usage
```python
from operator import itemgetter
from detikzify.model import load
from detikzify.infer import DetikzifyPipeline
import torch
image = "https://w.wiki/A7Cc"
pipeline = DetikzifyPipeline(*load(
base_model="nllg/detikzify-cl-7b",
device_map="auto",
torch_dtype=torch.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")
```