Instructions to use chongzicbo/MathImg2Latex with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chongzicbo/MathImg2Latex with Transformers:

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

pipe = pipeline("image-text-to-text", model="chongzicbo/MathImg2Latex")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("chongzicbo/MathImg2Latex")
model = AutoModelForImageTextToText.from_pretrained("chongzicbo/MathImg2Latex")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use chongzicbo/MathImg2Latex with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chongzicbo/MathImg2Latex"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chongzicbo/MathImg2Latex",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/chongzicbo/MathImg2Latex

SGLang

How to use chongzicbo/MathImg2Latex 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 "chongzicbo/MathImg2Latex" \
    --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": "chongzicbo/MathImg2Latex",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "chongzicbo/MathImg2Latex" \
        --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": "chongzicbo/MathImg2Latex",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use chongzicbo/MathImg2Latex with Docker Model Runner:
```
docker model run hf.co/chongzicbo/MathImg2Latex
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

github: https://github.com/chongzicbo/MathImg2Latex/tree/main

import torch
from PIL import Image
from transformers import VisionEncoderDecoderModel
from transformers.models.nougat import NougatTokenizerFast
from nougat_latex.util import process_raw_latex_code
from nougat_latex import NougatLaTexProcessor
os.environ["RUN_ON_GPU_IDs"] = "1"
device = torch.device("cpu")
model_path = "chongzicbo/MathImg2Latex"
tokenizer = NougatTokenizerFast.from_pretrained(model_path)
latex_processor = NougatLaTexProcessor.from_pretrained(model_path)
model = VisionEncoderDecoderModel.from_pretrained(model_path)
model.to(device)
img_path = "/data/code/MathOCR/MathImg2Latex/examples/test_data/test86_screenshot_bigger.jpg"
image = Image.open(img_path)
if not image.mode == "RGB":
    image = image.convert("RGB")

pixel_values = latex_processor(image, return_tensors="pt").pixel_values
task_prompt = tokenizer.bos_token
decoder_input_ids = tokenizer(
    task_prompt, add_special_tokens=False, return_tensors="pt"
).input_ids
with torch.no_grad():
    outputs = model.generate(
        pixel_values.to(device),
        decoder_input_ids=decoder_input_ids.to(device),
        max_length=model.decoder.config.max_length,
        early_stopping=True,
        pad_token_id=tokenizer.pad_token_id,
        eos_token_id=tokenizer.eos_token_id,
        use_cache=True,
        num_beams=1,
        bad_words_ids=[[tokenizer.unk_token_id]],
        return_dict_in_generate=True,
    )
sequence = tokenizer.batch_decode(outputs.sequences)[0]
sequence = (
    sequence.replace(tokenizer.eos_token, "")
    .replace(tokenizer.pad_token, "")
    .replace(tokenizer.bos_token, "")
)
sequence = process_raw_latex_code(sequence)
print(sequence)

Downloads last month: -

Safetensors

Model size

0.3B params

Tensor type

I64

F32

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support