Instructions to use nvidia/LocateAnything-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/LocateAnything-3B with Transformers:

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

pipe = pipeline("image-text-to-text", model="nvidia/LocateAnything-3B", 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("nvidia/LocateAnything-3B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nvidia/LocateAnything-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/LocateAnything-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/LocateAnything-3B",
		"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/nvidia/LocateAnything-3B

SGLang

How to use nvidia/LocateAnything-3B 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 "nvidia/LocateAnything-3B" \
    --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": "nvidia/LocateAnything-3B",
		"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 "nvidia/LocateAnything-3B" \
        --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": "nvidia/LocateAnything-3B",
		"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 nvidia/LocateAnything-3B with Docker Model Runner:
```
docker model run hf.co/nvidia/LocateAnything-3B
```

LocateAnything-3B

File size: 2,351 Bytes

d979fab

{
  "_attn_implementation": "magi",
  "_commit_hash": null,
  "architectures": [
    "LocateAnythingForConditionalGeneration"
  ],
  "auto_map": {
    "AutoConfig": "configuration_locateanything.LocateAnythingConfig",
    "AutoModel": "modeling_locateanything.LocateAnythingForConditionalGeneration"
  },
  "box_end_token_id": 151669,
  "box_start_token_id": 151668,
  "coord_end_token_id": 152677,
  "coord_start_token_id": 151677,
  "image_token_index": 151665,
  "mlp_checkpoint": false,
  "mlp_connector_layers": 2,
  "model_type": "locateanything",
  "none_token_id": 4064,
  "ref_end_token_id": 151673,
  "ref_start_token_id": 151672,
  "template": null,
  "text_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
    "architectures": [
      "Qwen2ForCausalLM"
    ],
    "attention_dropout": 0.0,
    "block_size": 6,
    "bos_token_id": 151643,
    "causal_attn": false,
    "eos_token_id": 151645,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "max_position_embeddings": 32768,
    "max_window_layers": 70,
    "model_type": "qwen2",
    "null_token_id": 152678,
    "num_attention_heads": 16,
    "num_hidden_layers": 36,
    "num_key_value_heads": 2,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000.0,
    "sliding_window": 32768,
    "switch_token_id": 152679,
    "text_mask_token_id": 151676,
    "tie_word_embeddings": true,
    "torch_dtype": "bfloat16",
    "use_cache": false,
    "use_sliding_window": false,
    "vocab_size": 152681
  },
  "torch_dtype": "bfloat16",
  "transformers_version": null,
  "use_backbone_lora": 0,
  "use_llm_lora": 0,
  "vision_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "moonshotai/MoonViT-SO-400M",
    "auto_map": {
      "AutoConfig": "moonshotai/MoonViT-SO-400M--configuration_moonvit.MoonViTConfig",
      "AutoModel": "moonshotai/MoonViT-SO-400M--modeling_moonvit.MoonVitPretrainedModel"
    },
    "hidden_size": 1152,
    "init_pos_emb_height": 64,
    "init_pos_emb_width": 64,
    "intermediate_size": 4304,
    "merge_kernel_size": [
      2,
      2
    ],
    "model_type": "moonvit",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "patch_size": 14,
    "torch_dtype": "bfloat16"
  }
}