nllg/datikz-v2
Viewer • Updated • 95k • 763 • 17
How to use nllg/detikzify-ds-7b with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="nllg/detikzify-ds-7b") # Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("nllg/detikzify-ds-7b", dtype="auto")How to use nllg/detikzify-ds-7b with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nllg/detikzify-ds-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "nllg/detikzify-ds-7b",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/nllg/detikzify-ds-7b
How to use nllg/detikzify-ds-7b with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "nllg/detikzify-ds-7b" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "nllg/detikzify-ds-7b",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "nllg/detikzify-ds-7b" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "nllg/detikzify-ds-7b",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use nllg/detikzify-ds-7b with Docker Model Runner:
docker model run hf.co/nllg/detikzify-ds-7b
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.
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")