Instructions to use HuggingFaceTB/SmolVLM-256M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceTB/SmolVLM-256M-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="HuggingFaceTB/SmolVLM-256M-Instruct")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM-256M-Instruct")
model = AutoModelForImageTextToText.from_pretrained("HuggingFaceTB/SmolVLM-256M-Instruct")
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

vLLM

How to use HuggingFaceTB/SmolVLM-256M-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/SmolVLM-256M-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/SmolVLM-256M-Instruct",
		"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/HuggingFaceTB/SmolVLM-256M-Instruct

SGLang

How to use HuggingFaceTB/SmolVLM-256M-Instruct 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 "HuggingFaceTB/SmolVLM-256M-Instruct" \
    --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": "HuggingFaceTB/SmolVLM-256M-Instruct",
		"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 "HuggingFaceTB/SmolVLM-256M-Instruct" \
        --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": "HuggingFaceTB/SmolVLM-256M-Instruct",
		"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 HuggingFaceTB/SmolVLM-256M-Instruct with Docker Model Runner:
```
docker model run hf.co/HuggingFaceTB/SmolVLM-256M-Instruct
```

Xenova HF Staff commited on Jan 20, 2025

Commit

192fb0b

verified ·

1 Parent(s): 5f7f5a3

Upload fixed vision ONNX weights (#2)

Browse files

- Upload fixed vision ONNX weights (389a8744f9df72b72e9e68d7e7c5b3147d5e9f67)

Files changed (8) hide show

onnx/vision_encoder.onnx +1 -1
onnx/vision_encoder_bnb4.onnx +1 -1
onnx/vision_encoder_fp16.onnx +1 -1
onnx/vision_encoder_int8.onnx +1 -1
onnx/vision_encoder_q4.onnx +1 -1
onnx/vision_encoder_q4f16.onnx +1 -1
onnx/vision_encoder_quantized.onnx +1 -1
onnx/vision_encoder_uint8.onnx +1 -1

onnx/vision_encoder.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddbb0b5a17ecedc6e50094cccb6cf22e654e64b3a1b949771de9f95680784cff
 size 374316497

 version https://git-lfs.github.com/spec/v1
+oid sha256:e27ad810eabfa7c881b409e1ca357e7a951541019add228ff73c72718fcf6218
 size 374316497

onnx/vision_encoder_bnb4.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c096208a9b64ec75fab9f9d2ad1c2ae4066789aba66bb9b0f9ce0aeacdd2d4ff
 size 58034739

 version https://git-lfs.github.com/spec/v1
+oid sha256:7d2b29e46fa0de326b63e92e751561cf28180d597ad0ad0859f92bf598944352
 size 58034739

onnx/vision_encoder_fp16.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d9ff4b8be30dd651544b0b4c2c2c58153c325150acdff4dc5be279873f062a
 size 187294693

 version https://git-lfs.github.com/spec/v1
+oid sha256:275c41d775508b7f7410580c4aaf67583a34acf23c31259effa8e53f67e8d9ae
 size 187294693

onnx/vision_encoder_int8.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189210601b3de235db7815791447a0cf7be8975c305ea300ca8214f833d3709a
 size 94247927

 version https://git-lfs.github.com/spec/v1
+oid sha256:d534ab668d3563e6d1d809bbbf1ff18308ded48651178614dbcc4a1de13d16f7
 size 94247927

onnx/vision_encoder_q4.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd7327fdcd1d05a09f8b712b901878498c2bc9e46a268784c2fa0e191eec9ca
 size 63784987

 version https://git-lfs.github.com/spec/v1
+oid sha256:95814e6629ec465e7cf98a44edcee67abc06d41faa0d1acc410cf8a956cab488
 size 63784987

onnx/vision_encoder_q4f16.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2004ce99abc34e4151be11fb85b20dfe6713e60fc0fd36a637d60e8856489184
 size 55037584

 version https://git-lfs.github.com/spec/v1
+oid sha256:13c301dc0cbc79c8c23badc699129b47d05ba044e2274ca8a94681fcd4205fc1
 size 55037584

onnx/vision_encoder_quantized.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:080bd15f32329b18af059ec46b8bb8c0f9524fab5065bad6ae76ddee0b034a9c
 size 94247969

 version https://git-lfs.github.com/spec/v1
+oid sha256:f82adc84246fbfe8651038470166385452682cc889538f5106544e622e5f1595
 size 94247969

onnx/vision_encoder_uint8.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:080bd15f32329b18af059ec46b8bb8c0f9524fab5065bad6ae76ddee0b034a9c
 size 94247969

 version https://git-lfs.github.com/spec/v1
+oid sha256:f82adc84246fbfe8651038470166385452682cc889538f5106544e622e5f1595
 size 94247969