Instructions to use merve/PaddleOCR-VL-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use merve/PaddleOCR-VL-hf with Transformers:

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

pipe = pipeline("image-text-to-text", model="merve/PaddleOCR-VL-hf")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("merve/PaddleOCR-VL-hf")
model = AutoModelForMultimodalLM.from_pretrained("merve/PaddleOCR-VL-hf", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PaddleOCR

How to use merve/PaddleOCR-VL-hf with PaddleOCR:

# Please refer to the document for information on how to use the model.
# https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/module_usage/module_overview.html

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use merve/PaddleOCR-VL-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "merve/PaddleOCR-VL-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "merve/PaddleOCR-VL-hf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/merve/PaddleOCR-VL-hf

SGLang

How to use merve/PaddleOCR-VL-hf 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 "merve/PaddleOCR-VL-hf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "merve/PaddleOCR-VL-hf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "merve/PaddleOCR-VL-hf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "merve/PaddleOCR-VL-hf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use merve/PaddleOCR-VL-hf with Docker Model Runner:
```
docker model run hf.co/merve/PaddleOCR-VL-hf
```

merve HF Staff commited on Feb 11

Commit

95c80fc

verified ·

1 Parent(s): 3ec0cc5

Upload processor

Browse files

Files changed (5) hide show

.gitattributes +1 -0
chat_template.jinja +43 -0
processor_config.json +32 -0
tokenizer.json +3 -0
tokenizer_config.json +27 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,43 @@

+{%- if not add_generation_prompt is defined -%}
+    {%- set add_generation_prompt = true -%}
+{%- endif -%}
+{%- if not cls_token is defined -%}
+    {%- set cls_token = "<|begin_of_sentence|>" -%}
+{%- endif -%}
+{%- if not eos_token is defined -%}
+    {%- set eos_token = "</s>" -%}
+{%- endif -%}
+{{- cls_token -}}
+{%- for message in messages -%}
+    {%- if message["role"] == "user" -%}
+        {{- "User: " -}}
+        {%- for content in message["content"] -%}
+            {%- if content["type"] == "image" -%}
+                {{ "<|IMAGE_START|><|IMAGE_PLACEHOLDER|><|IMAGE_END|>" }}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- for content in message["content"] -%}
+            {%- if content["type"] == "text" -%}
+                {{ content["text"] }}
+            {%- endif -%}
+        {%- endfor -%}
+        {{ "\n" -}}
+    {%- elif message["role"] == "assistant" -%}
+        {{- "Assistant: " -}}
+        {%- for content in message["content"] -%}
+            {%- if content["type"] == "text" -%}
+                {{ content["text"] }}
+            {%- endif -%}
+        {%- endfor -%}
+        {{ eos_token -}}
+    {%- elif message["role"] == "system" -%}
+        {%- for content in message["content"] -%}
+            {%- if content["type"] == "text" -%}
+                {{ content["text"] + "\n" }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "Assistant: " -}}
+{%- endif -%}

processor_config.json ADDED Viewed

	@@ -0,0 +1,32 @@

+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "PaddleOCRVLImageProcessorFast",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_pixels": 2822400,
+    "merge_size": 2,
+    "min_pixels": 147384,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 2822400,
+      "shortest_edge": 147384
+    },
+    "temporal_patch_size": 1
+  },
+  "processor_class": "PaddleOCRVLProcessor"
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f90f04fd8e5eb6dfa380f37d10c87392de8438dccb6768a2486b5a96ee76dba6
+size 11187679

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,27 @@

+{
+  "add_prefix_space": false,
+  "auto_map": {
+    "AutoProcessor": "processing_paddleocr_vl.PaddleOCRVLProcessor"
+  },
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<|begin_of_sentence|>",
+  "eos_token": "</s>",
+  "image_token": "<|IMAGE_PLACEHOLDER|>",
+  "is_local": true,
+  "legacy": true,
+  "mask_token": "<mask:1>",
+  "model_max_length": 131072,
+  "model_specific_special_tokens": {
+    "image_token": "<|IMAGE_PLACEHOLDER|>"
+  },
+  "pad_token": "<unk>",
+  "processor_class": "PaddleOCRVLProcessor",
+  "sep_token": "<|end_of_sentence|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}