license: cc-by-sa-4.0 base_model:

• vikp/texify pipeline_tag: image-to-text

texify-fp16-onnx

https://huggingface.co/vikp/texify 的 fp16 ONNX 权重版本，感谢 https://huggingface.co/Xenova/texify

用法 (optimum[onnxruntime])

如果你还没有安装，可以通过 onnxruntime 后端安装 optimum：

pip install \"optimum[onnxruntime-gpu]\"

示例：

from optimum.onnxruntime import ORTModelForVision2Seq
from optimum.pipelines import pipeline

model = ORTModelForVision2Seq.from_pretrained(\"Spedon/texify-fp16-onnx\", provider=\"CUDAExecutionProvider\")
texify = pipeline(
    \"image-to-text\",
    model,
    feature_extractor=\"Spedon/texify-fp16-onnx\",
    image_processor=\"Spedon/texify-fp16-onnx\",
)
image = (
    \"https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/latex.png\"
)
latex = texify(image, max_new_tokens=384)
print(latex)
# [{'generated_text': \"The potential $V_i$ of cell $\\mathcal{C}_i$ centred at position $\\mathbf{r}_i$ is related to the surface charge densities $\\sigma_j$ of cells $\\mathcal{C}_j$ $j\\in[1,N]$ through the superposition principle as: $$V_i\\,=\\,\\sum_{j=0}^{N}\\,\\frac{\\sigma_j}{4\\pi\\varepsilon_0}\\,\\int_{\\mathcal{C}_j}\\frac{1}{\\|\\mathbf{r}_i-\\mathbf{r}'\\|}\\,\\mathrm{d}^2\\mathbf{r}'\\,=\\,\\sum_{j=0}^{N}\\,Q_{ij}\\,\\sigma_j,$$ where the integral over the surface of cell $\\mathcal{C}_j$ only depends on $\\mathcal{C}_j$ shape and on the relative position of the target point $\\mathbf{r}_i$ with respect to $\\mathcal{C}_j$ location, as $\\sigma_j$ is assumed constant over the whole surface of cell $\\mathcal{C}_j$. \"}]

输入图像	可视化输出