Instructions to use xiwenyoumu/Fast-dDrive with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xiwenyoumu/Fast-dDrive with Transformers:

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

pipe = pipeline("image-text-to-text", model="xiwenyoumu/Fast-dDrive", 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)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("xiwenyoumu/Fast-dDrive", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use xiwenyoumu/Fast-dDrive with vLLM:

Install from pip and serve model

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

SGLang

How to use xiwenyoumu/Fast-dDrive 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 "xiwenyoumu/Fast-dDrive" \
    --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": "xiwenyoumu/Fast-dDrive",
		"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 "xiwenyoumu/Fast-dDrive" \
        --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": "xiwenyoumu/Fast-dDrive",
		"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 xiwenyoumu/Fast-dDrive with Docker Model Runner:
```
docker model run hf.co/xiwenyoumu/Fast-dDrive
```

Fast-dDrive

File size: 5,229 Bytes

5e9a603

{
  "always_mask_im_end": true,
  "anneal_block_size": false,
  "architectures": [
    "Fast_dDriveForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "bd_size": 32,
  "block_causal_no_dynamic": false,
  "complementary_mask": true,
  "deep_json_scaffold": true,
  "dtype": "float32",
  "enable_efficient_vision_embed": false,
  "entropy_loss": false,
  "entropy_loss_weight": 1.0,
  "eos_token_id": 151645,
  "flexible_bd_size": false,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "image_token_id": 151655,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 128000,
  "max_window_layers": 70,
  "minimum_noise_level": 0.001,
  "model_type": "fast_d_drive",
  "num_attention_heads": 16,
  "num_hidden_layers": 36,
  "num_key_value_heads": 2,
  "pad_token_id": 151643,
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "mrope_section": [
      16,
      24,
      24
    ],
    "rope_type": "default",
    "type": "default"
  },
  "rope_theta": 1000000.0,
  "section_block_steps": null,
  "section_loss_weights": {
    "critical_objects": 1.5,
    "explanation": 1.0,
    "future_meta_behavior": 2.0,
    "trajectory": 3.0
  },
  "section_noise_schedule": {
    "critical_objects": "1.0,2.0",
    "explanation": "1.0,1.0",
    "future_meta_behavior": "1.0,1.5",
    "trajectory": "2.0,1.0"
  },
  "section_token_budgets": null,
  "sliding_window": 32768,
  "static_json_scaffold": false,
  "text_config": {
    "always_mask_im_end": true,
    "anneal_block_size": false,
    "architectures": [
      "Fast_dDriveForConditionalGeneration"
    ],
    "attention_dropout": 0.0,
    "auto_map": {
      "AutoConfig": "configuration.Fast_dDriveConfig",
      "AutoModel": "modeling.Fast_dDriveForConditionalGeneration",
      "AutoModelForCausalLM": "modeling.Fast_dDriveForConditionalGeneration"
    },
    "bd_size": 32,
    "block_causal_no_dynamic": false,
    "block_length": null,
    "bos_token_id": 151643,
    "complementary_mask": true,
    "deep_json_scaffold": true,
    "dtype": "float32",
    "enable_efficient_vision_embed": false,
    "entropy_loss": false,
    "entropy_loss_weight": 1.0,
    "eos_token_id": 151645,
    "flexible_bd_size": false,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "image_token_id": null,
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "layer_types": [
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention"
    ],
    "max_position_embeddings": 128000,
    "max_window_layers": 70,
    "minimum_noise_level": 0.001,
    "model_type": "fast_d_drive_for_causal_lm",
    "num_attention_heads": 16,
    "num_hidden_layers": 36,
    "num_key_value_heads": 2,
    "rms_norm_eps": 1e-06,
    "rope_scaling": {
      "mrope_section": [
        16,
        24,
        24
      ],
      "rope_type": "default",
      "type": "default"
    },
    "rope_theta": 1000000.0,
    "section_block_steps": null,
    "section_token_budgets": null,
    "self_spec_inference_mode": null,
    "sliding_window": null,
    "static_json_scaffold": false,
    "tie_word_embeddings": true,
    "use_block_causal_mask": true,
    "use_cache": true,
    "use_json_scaffold": true,
    "use_sliding_window": false,
    "video_token_id": null,
    "vision_end_token_id": 151653,
    "vision_start_token_id": 151652,
    "vision_token_id": 151654,
    "vocab_size": 151936
  },
  "transformers_version": "4.57.1",
  "use_block_causal_mask": true,
  "use_cache": true,
  "use_json_scaffold": true,
  "use_sliding_window": false,
  "video_token_id": 151656,
  "vision_config": {
    "depth": 32,
    "dtype": "float32",
    "fullatt_block_indexes": [
      7,
      15,
      23,
      31
    ],
    "hidden_act": "silu",
    "hidden_size": 1280,
    "in_channels": 3,
    "in_chans": 3,
    "initializer_range": 0.02,
    "intermediate_size": 3420,
    "model_type": "fast_d_drive",
    "num_heads": 16,
    "out_hidden_size": 2048,
    "patch_size": 14,
    "spatial_merge_size": 2,
    "spatial_patch_size": 14,
    "temporal_patch_size": 2,
    "tokens_per_second": 2,
    "window_size": 112
  },
  "vision_end_token_id": 151653,
  "vision_start_token_id": 151652,
  "vision_token_id": 151654,
  "vocab_size": 151936,
  "auto_map": {
    "AutoConfig": "configuration.Fast_dDriveConfig",
    "AutoModel": "modeling.Fast_dDriveForConditionalGeneration",
    "AutoModelForCausalLM": "modeling.Fast_dDriveForConditionalGeneration"
  }
}