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>

convert_hf_to_gguf.py

@@ -3733,6 +3733,13 @@ class Ernie4_5Model(TextModel):
     def set_vocab(self):
         self._set_vocab_sentencepiece()
 
+        tokenizer_config_file = self.dir_model / 'tokenizer_config.json'
+        if tokenizer_config_file.is_file():
+            with open(tokenizer_config_file, "r", encoding="utf-8") as f:
+                tokenizer_config_json = json.load(f)
+                if "add_prefix_space" in tokenizer_config_json:
+                    self.gguf_writer.add_add_space_prefix(tokenizer_config_json["add_prefix_space"])
+
     def set_gguf_parameters(self):
         super().set_gguf_parameters()
 
@@ -3742,6 +3749,10 @@ class Ernie4_5Model(TextModel):
         if (head_dim := self.hparams.get("head_dim")) is None:
             head_dim = self.hparams["hidden_size"] // num_heads
 
+        if "mlp_AR" in name or "vision_model" in name:
+            # skip vision model and projector tensors
+            return
+
         if "ernie." in name:
             name = name.replace("ernie.", "model.")
         # split the qkv weights
@@ -3851,6 +3862,48 @@ class Ernie4_5MoeModel(Ernie4_5Model):
                 raise ValueError(f"Unprocessed experts: {experts}")
 
 
+@ModelBase.register("PaddleOCRVLForConditionalGeneration")
+class PaddleOCRModel(Ernie4_5Model):
+    model_arch = gguf.MODEL_ARCH.PADDLEOCR
+
+
+@ModelBase.register("PaddleOCRVisionModel")
+class PaddleOCRVisionModel(MmprojModel):
+    # PaddleOCR-VL uses a modified version of Siglip
+    min_pixels: int = 0
+    max_pixels: int = 0
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        assert self.hparams_vision is not None
+        self.min_pixels = self.preprocessor_config["min_pixels"]
+        self.max_pixels = self.preprocessor_config["max_pixels"]
+        self.hparams_vision["image_size"] = int(math.sqrt(self.max_pixels))
+
+    def set_gguf_parameters(self):
+        super().set_gguf_parameters()
+        assert self.hparams_vision is not None
+        hparams = self.hparams_vision
+        self.gguf_writer.add_clip_projector_type(gguf.VisionProjectorType.PADDLEOCR)
+        self.gguf_writer.add_vision_max_pixels(self.max_pixels)
+        self.gguf_writer.add_vision_min_pixels(self.min_pixels)
+        self.gguf_writer.add_vision_use_gelu(True)
+        self.gguf_writer.add_vision_attention_layernorm_eps(hparams.get("rms_norm_eps", 1e-6))
+
+    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
+        name = name.replace("visual.", "model.")
+
+        if "vision_model" in name or "mlp_AR" in name:
+            if "packing_position_embedding" in name:
+                return # unused
+            elif "vision_model.head" in name:
+                # we don't yet support image embeddings for this model
+                return
+            else:
+                yield from super().modify_tensors(data_torch, name, bid)
+        return # skip other tensors
+
+
 @ModelBase.register(
     "Qwen2VLModel",
     "Qwen2VLForConditionalGeneration",