Instructions to use rootlocalghost/Qianfan-OCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rootlocalghost/Qianfan-OCR with Transformers:

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

pipe = pipeline("image-text-to-text", model="rootlocalghost/Qianfan-OCR")
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("rootlocalghost/Qianfan-OCR")
model = AutoModelForMultimodalLM.from_pretrained("rootlocalghost/Qianfan-OCR")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rootlocalghost/Qianfan-OCR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rootlocalghost/Qianfan-OCR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rootlocalghost/Qianfan-OCR",
		"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/rootlocalghost/Qianfan-OCR

SGLang

How to use rootlocalghost/Qianfan-OCR 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 "rootlocalghost/Qianfan-OCR" \
    --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": "rootlocalghost/Qianfan-OCR",
		"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 "rootlocalghost/Qianfan-OCR" \
        --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": "rootlocalghost/Qianfan-OCR",
		"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 rootlocalghost/Qianfan-OCR with Docker Model Runner:
```
docker model run hf.co/rootlocalghost/Qianfan-OCR
```

rootlocalghost commited on May 2

Commit

3479e2e

verified ·

1 Parent(s): c18315d

clone chat_template.jinja

Browse files

Files changed (1) hide show

chat_template.jinja +77 -0

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,77 @@

+{%- if messages[0]['role'] == 'system' %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['content'] is string %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {%- for item in messages[0]['content'] %}
+            {%- if item['type'] == 'text' %}
+                {{- item['text'] }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {{- '<|im_start|>system\n你是Qianfan-VL，由百度智能云研发的多模态大语言模型。<|im_end|>\n' }}
+{%- endif %}
+{%- set ns = namespace(found_last_user=false, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if not ns.found_last_user and message['role'] == 'user' %}
+        {%- set ns.found_last_user = true %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if messages[0]['role'] != 'system' or not loop.first %}
+        {%- if message['role'] == 'user' or (message['role'] == 'system' and not loop.first) %}
+            {%- set append_think = (enable_thinking is defined and enable_thinking and message['role'] == 'user' and loop.index0 == ns.last_query_index) %}
+                {{- '<|im_start|>' + message['role'] + '\n' }}
+            {%- if message['content'] is string %}
+                {{- message['content'] }}
+            {%- else %}
+            {%- for item in message['content'] %}
+                {%- if item['type'] == 'image' %}
+                    {{- '<image>\n' }}
+                {%- elif item['type'] == 'video' %}
+                    {{- '<video>\n' }}
+                {%- elif item['type'] == 'text' %}
+                    {{- item['text'] }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if append_think %}
+            {{- '<think>' }}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+        {%- elif message['role'] == 'assistant' %}
+            {%- if message['content'] is string %}
+                {%- set raw_content = message['content'] %}
+            {%- else %}
+                {%- set content_ns = namespace(raw='') %}
+                {%- for item in message['content'] %}
+                    {%- if item['type'] == 'text' %}
+                        {%- set content_ns.raw = content_ns.raw + item['text'] %}
+                    {%- endif %}
+                {%- endfor %}
+                {%- set raw_content = content_ns.raw %}
+            {%- endif %}
+            {%- set content = raw_content %}
+            {%- set reasoning_content = '' %}
+            {%- if 'reasoning_content' in message and message['reasoning_content'] is not none %}
+                {%- set reasoning_content = message['reasoning_content'] %}
+            {%- elif '</think>' in raw_content %}
+                {%- set content = raw_content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = raw_content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+            {%- if loop.index0 > ns.last_query_index and reasoning_content %}
+                {{- '<|im_start|>' + message['role'] + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message['role'] + '\n' + content }}
+            {%- endif %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}