Instructions to use LiquidAI/d1-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/d1-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="LiquidAI/d1-2B", trust_remote_code=True)
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 AutoModel
model = AutoModel.from_pretrained("LiquidAI/d1-2B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LiquidAI/d1-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/d1-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LiquidAI/d1-2B",
		"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/LiquidAI/d1-2B

SGLang

How to use LiquidAI/d1-2B 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 "LiquidAI/d1-2B" \
    --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": "LiquidAI/d1-2B",
		"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 "LiquidAI/d1-2B" \
        --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": "LiquidAI/d1-2B",
		"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 LiquidAI/d1-2B with Docker Model Runner:
```
docker model run hf.co/LiquidAI/d1-2B
```

d1-2B / native_lfm3_vl.py

paulpak58

mlabonne

Aurelien-Lac

d1-2B

97c5704 about 3 hours ago

Raw History Blame Contribute Delete

1.39 kB

"""LFM3-VL's transformers classes (`native_lfm3`): its config, vision tower, picture and video processors."""

from __future__ import annotations

from .native_lfm3 import Lfm3Model  # noqa: F401  (registered: the VL builds its text model by config)

try:
    from transformers import Lfm3VlConfig, Lfm3VlForConditionalGeneration, Lfm3VlProcessor
except ImportError:
    from transformers import AutoConfig, AutoImageProcessor, AutoModel, AutoProcessor, AutoVideoProcessor

    from .configuration_lfm3_vl import Lfm3VlConfig, Lfm3VlVisionConfig
    from .image_processing_lfm3_vl import Lfm3VlImageProcessor
    from .modeling_lfm3_vl import Lfm3VlForConditionalGeneration, Lfm3VlVisionModel
    from .processing_lfm3_vl import Lfm3VlProcessor
    from .video_processing_lfm3_vl import Lfm3VlVideoProcessor

    for config in (Lfm3VlConfig, Lfm3VlVisionConfig):
        AutoConfig.register(config.model_type, config, exist_ok=True)
    AutoModel.register(Lfm3VlVisionConfig, Lfm3VlVisionModel, exist_ok=True)  # the tower, built by config
    AutoImageProcessor.register(Lfm3VlConfig, fast_image_processor_class=Lfm3VlImageProcessor, exist_ok=True)
    AutoVideoProcessor.register(Lfm3VlConfig, Lfm3VlVideoProcessor, exist_ok=True)
    AutoProcessor.register(Lfm3VlConfig, Lfm3VlProcessor, exist_ok=True)

__all__ = ["Lfm3VlConfig", "Lfm3VlForConditionalGeneration", "Lfm3VlProcessor"]

	"""LFM3-VL's transformers classes (`native_lfm3`): its config, vision tower, picture and video processors."""

	from __future__ import annotations

	from .native_lfm3 import Lfm3Model # noqa: F401 (registered: the VL builds its text model by config)

	try:
	from transformers import Lfm3VlConfig, Lfm3VlForConditionalGeneration, Lfm3VlProcessor
	except ImportError:
	from transformers import AutoConfig, AutoImageProcessor, AutoModel, AutoProcessor, AutoVideoProcessor

	from .configuration_lfm3_vl import Lfm3VlConfig, Lfm3VlVisionConfig
	from .image_processing_lfm3_vl import Lfm3VlImageProcessor
	from .modeling_lfm3_vl import Lfm3VlForConditionalGeneration, Lfm3VlVisionModel
	from .processing_lfm3_vl import Lfm3VlProcessor
	from .video_processing_lfm3_vl import Lfm3VlVideoProcessor

	for config in (Lfm3VlConfig, Lfm3VlVisionConfig):
	AutoConfig.register(config.model_type, config, exist_ok=True)
	AutoModel.register(Lfm3VlVisionConfig, Lfm3VlVisionModel, exist_ok=True) # the tower, built by config
	AutoImageProcessor.register(Lfm3VlConfig, fast_image_processor_class=Lfm3VlImageProcessor, exist_ok=True)
	AutoVideoProcessor.register(Lfm3VlConfig, Lfm3VlVideoProcessor, exist_ok=True)
	AutoProcessor.register(Lfm3VlConfig, Lfm3VlProcessor, exist_ok=True)

	__all__ = ["Lfm3VlConfig", "Lfm3VlForConditionalGeneration", "Lfm3VlProcessor"]