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 19, 2025

Commit

41a32be

verified ·

1 Parent(s): 38591c2

Upload ONNX weights

Browse files

Files changed (24) hide show

onnx/decoder_model_merged.onnx +3 -0
onnx/decoder_model_merged_bnb4.onnx +3 -0
onnx/decoder_model_merged_fp16.onnx +3 -0
onnx/decoder_model_merged_int8.onnx +3 -0
onnx/decoder_model_merged_q4.onnx +3 -0
onnx/decoder_model_merged_q4f16.onnx +3 -0
onnx/decoder_model_merged_quantized.onnx +3 -0
onnx/decoder_model_merged_uint8.onnx +3 -0
onnx/embed_tokens.onnx +3 -0
onnx/embed_tokens_bnb4.onnx +3 -0
onnx/embed_tokens_fp16.onnx +3 -0
onnx/embed_tokens_int8.onnx +3 -0
onnx/embed_tokens_q4.onnx +3 -0
onnx/embed_tokens_q4f16.onnx +3 -0
onnx/embed_tokens_quantized.onnx +3 -0
onnx/embed_tokens_uint8.onnx +3 -0
onnx/vision_encoder.onnx +3 -0
onnx/vision_encoder_bnb4.onnx +3 -0
onnx/vision_encoder_fp16.onnx +3 -0
onnx/vision_encoder_int8.onnx +3 -0
onnx/vision_encoder_q4.onnx +3 -0
onnx/vision_encoder_q4f16.onnx +3 -0
onnx/vision_encoder_quantized.onnx +3 -0
onnx/vision_encoder_uint8.onnx +3 -0

onnx/decoder_model_merged.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2817946df1e3b4c99ad196995338edc1c1c0d8423d3b5153da77f67f8c2efc0a
+size 540971996

onnx/decoder_model_merged_bnb4.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1b8ba5c04aa524c2a3cdcba4825df38b24c04619ecffa6c6afcc77220f565bb3
+size 78486591

onnx/decoder_model_merged_fp16.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:982c6a62b11202086c4237ad80d59488b51c62ba1a0fc9cda68201590195397d
+size 270745787

onnx/decoder_model_merged_int8.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5580b6f2f49fa7c034cd67ba12196b11d5ab5162d7318baf48ead494e45944ca
+size 137553014

onnx/decoder_model_merged_q4.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f67dd06edf4edbbfeca36f79aaa1b3ea934a2b166d462b3b152788ec3232cd
+size 86894595

onnx/decoder_model_merged_q4f16.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ae568227d5e4ff2ce9a318218002574994c5325158c293eaacbc6e2ab807f889
+size 77366164

onnx/decoder_model_merged_quantized.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d19fafe563a1277492b94a562eda7c5c01a27373b2ee4cb4e716713d261a93
+size 137553128

onnx/decoder_model_merged_uint8.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d19fafe563a1277492b94a562eda7c5c01a27373b2ee4cb4e716713d261a93
+size 137553128

onnx/embed_tokens.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a68ea4058524059ed0e2873fdbc4f33b93e13ae3d3204938d32d0566d390ae00
+size 113541419

onnx/embed_tokens_bnb4.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:47ed7029703cff586fd719d70251324766a6591c8a58d315076b1781a65fc900
+size 113541438

onnx/embed_tokens_fp16.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:019af59078b8e4775216dd278c66574c39bfefa36cab68573db64d7ac7a11691
+size 56770946

onnx/embed_tokens_int8.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4b919b829fe2bf225e42431230c56891116f0149e5170e36c99bcc0cfae0d2ef
+size 28385824

onnx/embed_tokens_q4.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:47ed7029703cff586fd719d70251324766a6591c8a58d315076b1781a65fc900
+size 113541438

onnx/embed_tokens_q4f16.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d810e0849eda8128be2d9cf1a2be9ca0bd8e5bfbe5bf972f60ea8e2a566f6bfe
+size 56770965

onnx/embed_tokens_quantized.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4b919b829fe2bf225e42431230c56891116f0149e5170e36c99bcc0cfae0d2ef
+size 28385824

onnx/embed_tokens_uint8.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4b919b829fe2bf225e42431230c56891116f0149e5170e36c99bcc0cfae0d2ef
+size 28385824

onnx/vision_encoder.onnx ADDED Viewed

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

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

onnx/vision_encoder_bnb4.onnx ADDED Viewed

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

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

onnx/vision_encoder_fp16.onnx ADDED Viewed

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

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

onnx/vision_encoder_int8.onnx ADDED Viewed

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

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

onnx/vision_encoder_q4.onnx ADDED Viewed

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

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

onnx/vision_encoder_q4f16.onnx ADDED Viewed

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

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

onnx/vision_encoder_quantized.onnx ADDED Viewed

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

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

onnx/vision_encoder_uint8.onnx ADDED Viewed

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

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