Instructions to use VietAlphaLabs/SenOCR-Vi-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VietAlphaLabs/SenOCR-Vi-INT8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="VietAlphaLabs/SenOCR-Vi-INT8")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("VietAlphaLabs/SenOCR-Vi-INT8")
model = AutoModelForMultimodalLM.from_pretrained("VietAlphaLabs/SenOCR-Vi-INT8", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use VietAlphaLabs/SenOCR-Vi-INT8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VietAlphaLabs/SenOCR-Vi-INT8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VietAlphaLabs/SenOCR-Vi-INT8",
		"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/VietAlphaLabs/SenOCR-Vi-INT8

SGLang

How to use VietAlphaLabs/SenOCR-Vi-INT8 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 "VietAlphaLabs/SenOCR-Vi-INT8" \
    --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": "VietAlphaLabs/SenOCR-Vi-INT8",
		"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 "VietAlphaLabs/SenOCR-Vi-INT8" \
        --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": "VietAlphaLabs/SenOCR-Vi-INT8",
		"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 VietAlphaLabs/SenOCR-Vi-INT8 with Docker Model Runner:
```
docker model run hf.co/VietAlphaLabs/SenOCR-Vi-INT8
```

SenOCR-Vi-INT8

File size: 772 Bytes

b7baa54

{
  "source_repo": "VietAlphaLabs/SenOCR-Vi",
  "source_revision": "9c52e6f53ef85434be57f51a8993d7facf12c2f6",
  "loader": "transformers native PaddleOCRVLForConditionalGeneration (no trust_remote_code)",
  "method": "torchao Int8WeightOnlyConfig (per-row symmetric INT8 weights, BF16 activations)",
  "calibration_data": null,
  "quantized_modules": "all nn.Linear under model.language_model.layers. (q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj)",
  "quantized_linear_count": 126,
  "kept_bf16": [
    "model.visual",
    "model.projector",
    "lm_head",
    "model.language_model.embed_tokens",
    "norms"
  ],
  "versions": {
    "torch": "2.13.0+cpu",
    "torchao": "0.18.0",
    "transformers": "5.18.0"
  },
  "evaluated": false
}