Instructions to use hf-internal-testing/tiny-muse-spark with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-muse-spark with Transformers:

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

pipe = pipeline("image-text-to-text", model="hf-internal-testing/tiny-muse-spark")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("hf-internal-testing/tiny-muse-spark")
model = AutoModelForMultimodalLM.from_pretrained("hf-internal-testing/tiny-muse-spark", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hf-internal-testing/tiny-muse-spark with vLLM:

Install from pip and serve model

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

SGLang

How to use hf-internal-testing/tiny-muse-spark 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 "hf-internal-testing/tiny-muse-spark" \
    --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": "hf-internal-testing/tiny-muse-spark",
		"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 "hf-internal-testing/tiny-muse-spark" \
        --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": "hf-internal-testing/tiny-muse-spark",
		"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 hf-internal-testing/tiny-muse-spark with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-muse-spark
```

tiny-muse-spark

File size: 4,062 Bytes

bdf8cbd

{
  "architectures": [
    "MuseSparkForConditionalGeneration"
  ],
  "audio_config": {
    "conv_kernel_size": 7,
    "depths": [
      2,
      2,
      2,
      2
    ],
    "hidden_act": "gelu",
    "hidden_sizes": [
      256,
      512,
      1024,
      2048
    ],
    "initializer_range": 0.02,
    "mlp_ratio": 4.0,
    "model_type": "muse_spark_audio",
    "num_hidden_layers": 4,
    "out_hidden_size": 8192,
    "patch_sizes": [
      16,
      6,
      5,
      4
    ],
    "rms_norm_eps": 1e-06
  },
  "audio_token_id": 200038,
  "dtype": "bfloat16",
  "image_token_id": 200092,
  "model_type": "muse_spark",
  "out_hidden_size": 6144,
  "projector_hidden_act": "gelu",
  "projector_hidden_size": 4096,
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 200000,
    "eos_token_id": 200001,
    "final_logit_softcapping": 20.0,
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 8192,
    "initializer_range": 0.02,
    "intermediate_size": 16384,
    "layer_rope_theta": [
      500000.0,
      0,
      500000.0,
      500000.0,
      500000.0,
      0
    ],
    "layer_types": [
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention"
    ],
    "max_position_embeddings": 1048576,
    "mlp_layer_types": [
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse"
    ],
    "model_type": "muse_spark_text",
    "moe_hidden_size": 4096,
    "moe_intermediate_size": 4096,
    "num_attention_heads": 128,
    "num_experts_per_tok": 8,
    "num_hidden_layers": 6,
    "num_key_value_heads": 16,
    "num_local_experts": 8,
    "num_shared_experts": 0,
    "output_multiplier": 0.17677669529663687,
    "pad_token_id": 200018,
    "post_norm_eps": 1e-08,
    "qk_scale_factor": 5.4730064863875,
    "residual_gate_temperature": 0.3,
    "rms_norm_eps": 1e-05,
    "rope_parameters": {
      "rope_theta": 500000.0,
      "rope_type": "default"
    },
    "routed_scaling_factor": 1.0,
    "sliding_window": 2048,
    "tie_word_embeddings": false,
    "use_cache": true,
    "vocab_size": 202048
  },
  "transformers_version": "5.18.0.dev0",
  "video_token_id": 200091,
  "vision_config": {
    "hidden_act": "gelu",
    "hidden_size": 1536,
    "intermediate_size": 8960,
    "layer_norm_eps": 1e-05,
    "layer_types": [
      "window_attention",
      "window_attention",
      "window_attention",
      "full_attention",
      "window_attention",
      "window_attention",
      "window_attention",
      "full_attention",
      "window_attention",
      "window_attention",
      "window_attention",
      "full_attention",
      "window_attention",
      "window_attention",
      "window_attention",
      "full_attention",
      "window_attention",
      "window_attention",
      "window_attention",
      "full_attention",
      "window_attention",
      "window_attention",
      "window_attention",
      "full_attention",
      "window_attention",
      "window_attention",
      "window_attention",
      "full_attention",
      "window_attention",
      "window_attention",
      "window_attention",
      "full_attention",
      "window_attention",
      "window_attention",
      "window_attention",
      "full_attention",
      "window_attention",
      "window_attention",
      "window_attention",
      "full_attention",
      "window_attention",
      "window_attention",
      "window_attention",
      "full_attention",
      "window_attention",
      "window_attention",
      "window_attention",
      "full_attention",
      "window_attention",
      "full_attention"
    ],
    "max_position_embeddings": 1024,
    "merge_size": 2,
    "model_type": "muse_spark_vision",
    "num_attention_heads": 16,
    "num_hidden_layers": 50,
    "patch_size": 14,
    "patch_temporal": 2,
    "pos_emb_height": 32,
    "pos_emb_width": 32,
    "rope_parameters": {
      "rope_theta": 10000,
      "rope_type": "axial"
    }
  }
}