model: Add PaddleOCR-VL model support (#18825)
* support PaddleOCR-VL * clip: update PaddleOCR model loader parameters to prevent OOM during warmup * [update] add paddleocr vl text model instead of ernie4.5 * [update] restore change of minicpmv * [update] format * [update] format * [update] positions and patch merge permute * [update] mtmd_decode_use_mrope for paddleocr * [update] image min/max pixels * [update] remove set_limit_image_tokens * upate: preprocess without padding * clean up * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
@@ -325,6 +325,10 @@ struct mtmd_context {
|
||||
img_beg = "<|begin_of_image|>";
|
||||
img_end = "<|end_of_image|>";
|
||||
|
||||
} else if (proj == PROJECTOR_TYPE_PADDLEOCR) {
|
||||
// <|IMAGE_START|> ... (image embeddings) ... <|IMAGE_END|>
|
||||
img_beg = "<|IMAGE_START|>";
|
||||
img_end = "<|IMAGE_END|>";
|
||||
}
|
||||
}
|
||||
|
||||
@@ -890,6 +894,7 @@ bool mtmd_decode_use_mrope(mtmd_context * ctx) {
|
||||
case PROJECTOR_TYPE_QWEN25VL:
|
||||
case PROJECTOR_TYPE_QWEN3VL:
|
||||
case PROJECTOR_TYPE_GLM4V:
|
||||
case PROJECTOR_TYPE_PADDLEOCR:
|
||||
return true;
|
||||
default:
|
||||
return false;
|
||||
|
||||
Reference in New Issue
Block a user