Instructions to use meta-models/Muse-Glimmer-30B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-models/Muse-Glimmer-30B with Transformers:

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

pipe = pipeline("image-text-to-text", model="meta-models/Muse-Glimmer-30B")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("meta-models/Muse-Glimmer-30B")
model = AutoModelForMultimodalLM.from_pretrained("meta-models/Muse-Glimmer-30B", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meta-models/Muse-Glimmer-30B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-models/Muse-Glimmer-30B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-models/Muse-Glimmer-30B",
		"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/meta-models/Muse-Glimmer-30B

SGLang

How to use meta-models/Muse-Glimmer-30B 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 "meta-models/Muse-Glimmer-30B" \
    --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": "meta-models/Muse-Glimmer-30B",
		"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 "meta-models/Muse-Glimmer-30B" \
        --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": "meta-models/Muse-Glimmer-30B",
		"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 meta-models/Muse-Glimmer-30B with Docker Model Runner:
```
docker model run hf.co/meta-models/Muse-Glimmer-30B
```

NVFP4, DFlash working on vLLM!

#30

by cloudnathan5 - opened 1 day ago

Discussion

cloudnathan5

1 day ago

Hey everyone. I tried this 'PR of a PR' of vLLM from xianbaoqian on GitHub on an RTX Pro 6000, and it was able to run the new Glimmer model with DFlash enabled and also supported various quants of the base model such as FP8 and NVFP4. I was able to achieve 140 tps decode with NVFP4 and DFlash enabled compared to the 120 ish I was seeing with UD Q4 K XL and DFlash on llama.cpp.

When trying FP8 I quantized on the fly. The NVFP4 quant I tried was the one I produced at https://huggingface.co/cloudnathan5/Muse-Glimmer-30B-NVFP4. That HF Repo also has commands you can reference to run it yourself.

Hope this helps anyone trying to run the model on vLLM or who is looking for an NVFP4 quantization.

Thank you Meta and all open-source contributors who made this possible!

g-a-b-y

about 12 hours ago

See https://huggingface.co/RedHatAI/Muse-Glimmer-30B-NVFP4

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment