959 2 weeks ago

PaddleOCR-VL is a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) .

0.9b
77c25c0df517 · 35B
{
"num_ctx": 4096,
"temperature": 0.7
}