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.py

paulpak58

mlabonne

Aurelien-Lac

d1-2B

97c5704 about 3 hours ago

Raw History Blame Contribute Delete

1.27 kB

"""LFM3's transformers classes, one module a model type: `native_lfm3` (text), `native_lfm3_vl` (pictures),
`native_lfm3_omni` (pictures and audio), each importing the one before it, so a Hub repository serves only its
model's files. transformers' own classes once a release ships them; until then copies of transformers' LFM3 code
beside these (each names its commit), registered with the Auto classes, so a checkpoint's config, tokenizer and
processor load and the composite models build their parts.
Shipping LFM3, transformers makes the fallbacks dead: delete them and the copies (the files headed "Vendored from"),
nothing else."""

from __future__ import annotations

try:
    from transformers import Lfm3Config, Lfm3ForCausalLM, Lfm3Model
except ImportError:
    from transformers import AutoConfig, AutoModel

    from .configuration_lfm3 import Lfm3Config
    from .modeling_lfm3 import Lfm3ForCausalLM, Lfm3Model

    # exist_ok: a second copy of these files in one process (two snapshots) registers again
    AutoConfig.register(Lfm3Config.model_type, Lfm3Config, exist_ok=True)
    AutoModel.register(Lfm3Config, Lfm3Model, exist_ok=True)  # the composite models build their text model by config

__all__ = ["Lfm3Config", "Lfm3ForCausalLM", "Lfm3Model"]

	"""LFM3's transformers classes, one module a model type: `native_lfm3` (text), `native_lfm3_vl` (pictures),
	`native_lfm3_omni` (pictures and audio), each importing the one before it, so a Hub repository serves only its
	model's files. transformers' own classes once a release ships them; until then copies of transformers' LFM3 code
	beside these (each names its commit), registered with the Auto classes, so a checkpoint's config, tokenizer and
	processor load and the composite models build their parts.

	Shipping LFM3, transformers makes the fallbacks dead: delete them and the copies (the files headed "Vendored from"),
	nothing else."""

	from __future__ import annotations

	try:
	from transformers import Lfm3Config, Lfm3ForCausalLM, Lfm3Model
	except ImportError:
	from transformers import AutoConfig, AutoModel

	from .configuration_lfm3 import Lfm3Config
	from .modeling_lfm3 import Lfm3ForCausalLM, Lfm3Model

	# exist_ok: a second copy of these files in one process (two snapshots) registers again
	AutoConfig.register(Lfm3Config.model_type, Lfm3Config, exist_ok=True)
	AutoModel.register(Lfm3Config, Lfm3Model, exist_ok=True) # the composite models build their text model by config

	__all__ = ["Lfm3Config", "Lfm3ForCausalLM", "Lfm3Model"]