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
```

guarin HF Staff commited on 3 days ago

Commit

707ff60

verified ·

1 Parent(s): bdf8cbd

Update chat template

Browse files

Files changed (1) hide show

chat_template.jinja +6 -3

chat_template.jinja CHANGED Viewed

@@ -1,9 +1,12 @@
 {%- set tools = tools | default(none) -%}
 {%- set add_generation_prompt = add_generation_prompt | default(false) -%}
-{%- set reasoning_effort = reasoning_effort | default('medium') -%}
 {%- set cutoff_date = cutoff_date | default('2026-01-04') -%}
 {%- set current_date = current_date | default(strftime_now('%Y-%m-%d') if strftime_now is defined else none) -%}
-{%- set reasoning_effort_map = {'minimal': 1, 'low': 16, 'medium': 64, 'high': 256, 'xhigh': 512} -%}
 {#- Neutralise control sequences in caller-supplied text so it cannot be
     tokenized as structure. "<|" is broken because every special token has the
@@ -142,7 +145,7 @@
 {%- if tools -%}
     {%- set sys.parts = sys.parts + [render_tool_defs(tools) | trim] -%}
 {%- endif -%}
-{%- if reasoning_effort in reasoning_effort_map and 'reasoning strength:' not in ((ns.instructions if ns.instructions else '') | lower) -%}
     {%- set sys.parts = sys.parts + ['Reasoning strength: ' ~ reasoning_effort_map[reasoning_effort] ~ '.'] -%}
 {%- endif -%}
 {%- set sys.parts = sys.parts + [render_valid_recipients(tools) | trim] -%}

 {%- set tools = tools | default(none) -%}
 {%- set add_generation_prompt = add_generation_prompt | default(false) -%}
+{%- set reasoning_effort = reasoning_effort | default('xhigh', true) -%}
 {%- set cutoff_date = cutoff_date | default('2026-01-04') -%}
 {%- set current_date = current_date | default(strftime_now('%Y-%m-%d') if strftime_now is defined else none) -%}
+{%- set reasoning_effort_map = {'low': 8, 'medium': 32, 'high': 256, 'xhigh': 512} -%}
+{%- if not (reasoning_effort is string and reasoning_effort in reasoning_effort_map) -%}
+    {{- raise_exception('Unsupported reasoning_effort: ' ~ reasoning_effort ~ '. Expected one of: low, medium, high, xhigh.') -}}
+{%- endif -%}
 {#- Neutralise control sequences in caller-supplied text so it cannot be
     tokenized as structure. "<|" is broken because every special token has the
 {%- if tools -%}
     {%- set sys.parts = sys.parts + [render_tool_defs(tools) | trim] -%}
 {%- endif -%}
+{%- if 'reasoning strength:' not in ((ns.instructions if ns.instructions else '') | lower) -%}
     {%- set sys.parts = sys.parts + ['Reasoning strength: ' ~ reasoning_effort_map[reasoning_effort] ~ '.'] -%}
 {%- endif -%}
 {%- set sys.parts = sys.parts + [render_valid_recipients(tools) | trim] -%}