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 / config.json

paulpak58

mlabonne

Aurelien-Lac

d1-2B

97c5704 about 6 hours ago

Raw History Blame Contribute Delete

2.9 kB

{
  "architectures": [
    "D1Model"
  ],
  "bos_token_id": 124894,
  "downsample_factor": 2,
  "dtype": "bfloat16",
  "eos_token_id": 124900,
  "image_token_id": 125030,
  "model_type": "lfm3_vl",
  "pad_token_id": 124893,
  "projector_bias": true,
  "projector_hidden_act": "gelu",
  "projector_hidden_size": 4096,
  "projector_layer_norm_eps": 1e-06,
  "text_config": {
    "bos_token_id": 124894,
    "conv_L_cache": 7,
    "conv_bias": false,
    "dtype": "bfloat16",
    "eos_token_id": 124900,
    "head_dim": 128,
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 7680,
    "layer_types": [
      "conv",
      "conv",
      "full_attention",
      "conv",
      "sliding_attention",
      "conv",
      "full_attention",
      "conv",
      "sliding_attention",
      "conv",
      "full_attention",
      "conv",
      "sliding_attention",
      "conv",
      "full_attention",
      "conv",
      "sliding_attention",
      "conv",
      "full_attention",
      "conv",
      "sliding_attention",
      "conv",
      "full_attention",
      "conv"
    ],
    "max_position_embeddings": 128000,
    "model_type": "lfm3",
    "norm_eps": 1e-05,
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "num_key_value_heads": 4,
    "pad_token_id": 124893,
    "rope_parameters": {
      "full_attention": {
        "partial_rotary_factor": 0.5,
        "rope_theta": 1000000.0,
        "rope_type": "default"
      },
      "sliding_attention": {
        "rope_theta": 10000,
        "rope_type": "default"
      }
    },
    "sliding_window": 256,
    "tie_word_embeddings": true,
    "use_cache": true,
    "use_sandwich_norm": true,
    "vocab_size": 128000
  },
  "tie_word_embeddings": true,
  "transformers_version": "5.19.0",
  "video_token_id": 125029,
  "vision_config": {
    "conv_kernel_size": 3,
    "dtype": "bfloat16",
    "hidden_size": 1024,
    "in_channels": 3,
    "initializer_range": 0.02,
    "intermediate_size": 2560,
    "layer_types": [
      "conv",
      "conv",
      "full_attention",
      "conv",
      "full_attention",
      "conv",
      "full_attention",
      "conv",
      "full_attention",
      "conv",
      "full_attention",
      "conv",
      "full_attention",
      "conv"
    ],
    "model_type": "lfm3_vl_vision",
    "norm_eps": 1e-05,
    "num_attention_heads": 16,
    "num_hidden_layers": 14,
    "num_key_value_heads": 8,
    "patch_size": 16,
    "rope_parameters": {
      "rope_theta": 1000000.0,
      "rope_type": "axial"
    },
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
  },
  "vision_end_token_id": 125010,
  "vision_start_token_id": 125009,
  "d1_codes": 2,
  "d1_attention": "set",
  "d1_numbers": true,
  "d1_set_size": 16,
  "d1_vision_max_pixels": 1638400,
  "auto_map": {
    "AutoModel": "modeling_d1_lfm3_vl.D1Model",
    "AutoConfig": "native_lfm3_vl.Lfm3VlConfig"
  }
}

	{
	"architectures": [
	"D1Model"
	],
	"bos_token_id": 124894,
	"downsample_factor": 2,
	"dtype": "bfloat16",
	"eos_token_id": 124900,
	"image_token_id": 125030,
	"model_type": "lfm3_vl",
	"pad_token_id": 124893,
	"projector_bias": true,
	"projector_hidden_act": "gelu",
	"projector_hidden_size": 4096,
	"projector_layer_norm_eps": 1e-06,
	"text_config": {
	"bos_token_id": 124894,
	"conv_L_cache": 7,
	"conv_bias": false,
	"dtype": "bfloat16",
	"eos_token_id": 124900,
	"head_dim": 128,
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 7680,
	"layer_types": [
	"conv",
	"conv",
	"full_attention",
	"conv",
	"sliding_attention",
	"conv",
	"full_attention",
	"conv",
	"sliding_attention",
	"conv",
	"full_attention",
	"conv",
	"sliding_attention",
	"conv",
	"full_attention",
	"conv",
	"sliding_attention",
	"conv",
	"full_attention",
	"conv",
	"sliding_attention",
	"conv",
	"full_attention",
	"conv"
	],
	"max_position_embeddings": 128000,
	"model_type": "lfm3",
	"norm_eps": 1e-05,
	"num_attention_heads": 16,
	"num_hidden_layers": 24,
	"num_key_value_heads": 4,
	"pad_token_id": 124893,
	"rope_parameters": {
	"full_attention": {
	"partial_rotary_factor": 0.5,
	"rope_theta": 1000000.0,
	"rope_type": "default"
	},
	"sliding_attention": {
	"rope_theta": 10000,
	"rope_type": "default"
	}
	},
	"sliding_window": 256,
	"tie_word_embeddings": true,
	"use_cache": true,
	"use_sandwich_norm": true,
	"vocab_size": 128000
	},
	"tie_word_embeddings": true,
	"transformers_version": "5.19.0",
	"video_token_id": 125029,
	"vision_config": {
	"conv_kernel_size": 3,
	"dtype": "bfloat16",
	"hidden_size": 1024,
	"in_channels": 3,
	"initializer_range": 0.02,
	"intermediate_size": 2560,
	"layer_types": [
	"conv",
	"conv",
	"full_attention",
	"conv",
	"full_attention",
	"conv",
	"full_attention",
	"conv",
	"full_attention",
	"conv",
	"full_attention",
	"conv",
	"full_attention",
	"conv"
	],
	"model_type": "lfm3_vl_vision",
	"norm_eps": 1e-05,
	"num_attention_heads": 16,
	"num_hidden_layers": 14,
	"num_key_value_heads": 8,
	"patch_size": 16,
	"rope_parameters": {
	"rope_theta": 1000000.0,
	"rope_type": "axial"
	},
	"spatial_merge_size": 2,
	"temporal_patch_size": 2
	},
	"vision_end_token_id": 125010,
	"vision_start_token_id": 125009,
	"d1_codes": 2,
	"d1_attention": "set",
	"d1_numbers": true,
	"d1_set_size": 16,
	"d1_vision_max_pixels": 1638400,
	"auto_map": {
	"AutoModel": "modeling_d1_lfm3_vl.D1Model",
	"AutoConfig": "native_lfm3_vl.Lfm3VlConfig"
	}
	}