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
```

Qianfan-OCR / config.json

rootlocalghost

clone config.json

152c7fa verified 2 months ago

Raw

History Blame

1.98 kB

	{
	"architectures": [
	"QianfanOCRForConditionalGeneration"
	],
	"downsample_ratio": 0.5,
	"dynamic_image_size": true,
	"eos_token_id": 151645,
	"force_image_size": 448,
	"image_token_id": 151671,
	"text_config": {
	"_name_or_path": "/root/codespace/checkpoints/Qwen3-4B",
	"architectures": [
	"Qwen3ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 151643,
	"debug": false,
	"eos_token_id": 151645,
	"ep_size": 1,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 2560,
	"initializer_range": 0.02,
	"intermediate_size": 9728,
	"max_position_embeddings": 32768,
	"max_window_layers": 36,
	"micro_forward": false,
	"model_type": "qwen3",
	"num_attention_heads": 32,
	"num_hidden_layers": 36,
	"num_key_value_heads": 8,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 5000000,
	"skip_checkpoint": false,
	"sliding_window": null,
	"torch_dtype": "bfloat16",
	"use_cache": false,
	"use_deepep": false,
	"use_sliding_window": false,
	"vocab_size": 153678
	},
	"max_dynamic_patch": 12,
	"min_dynamic_patch": 1,
	"model_type": "qianfan_ocr",
	"pad2square": false,
	"pad_token_id": 151643,
	"ps_version": "v2",
	"select_layer": -1,
	"template": "internvl2_5",
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": null,
	"use_thumbnail": true,
	"vision_config": {
	"architectures": [
	"QianfanOCRVisionModel"
	],
	"attention_dropout": 0.0,
	"drop_path_rate": 0.1,
	"hidden_act": "gelu",
	"hidden_size": 1024,
	"image_size": 448,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"layer_norm_eps": 1e-06,
	"model_type": "qianfan_ocr_vision",
	"norm_type": "layer_norm",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 24,
	"patch_size": 14,
	"qkv_bias": true,
	"torch_dtype": "bfloat16"
	}
	}