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

Libraries

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

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

pipe = pipeline("image-text-to-text", model="RedHatAI/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("RedHatAI/Muse-Glimmer-30B")
model = AutoModelForMultimodalLM.from_pretrained("RedHatAI/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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/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": "RedHatAI/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/RedHatAI/Muse-Glimmer-30B

SGLang

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

Muse-Glimmer-30B / config.json

robgreenberg3

Duplicate from meta-models/Muse-Glimmer-30B

0d89dcc about 11 hours ago

Raw

History Blame Contribute Delete

5.11 kB

	{
	"architectures": [
	"MuseGlimmerForConditionalGeneration"
	],
	"dtype": "bfloat16",
	"image_token_id": 200092,
	"model_type": "muse_glimmer",
	"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": 128,
	"hidden_activation": "silu",
	"hidden_size": 6656,
	"initializer_range": 0.02,
	"intermediate_size": 19968,
	"layer_rope_theta": [
	500000.0,
	500000.0,
	500000.0,
	0,
	500000.0,
	500000.0,
	500000.0,
	0,
	500000.0,
	500000.0,
	500000.0,
	0,
	500000.0,
	500000.0,
	500000.0,
	0,
	500000.0,
	500000.0,
	500000.0,
	0,
	500000.0,
	500000.0,
	500000.0,
	0,
	500000.0,
	500000.0,
	500000.0,
	0,
	500000.0,
	500000.0,
	500000.0,
	0,
	500000.0,
	500000.0,
	500000.0,
	0,
	500000.0,
	500000.0,
	500000.0,
	0,
	500000.0,
	500000.0,
	500000.0,
	0,
	500000.0,
	500000.0,
	500000.0,
	0,
	500000.0,
	500000.0,
	500000.0,
	0
	],
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 131072,
	"model_type": "muse_glimmer_text",
	"num_attention_heads": 32,
	"num_hidden_layers": 52,
	"num_key_value_heads": 2,
	"output_multiplier": 0.19611613513818404,
	"pad_token_id": null,
	"post_norm_eps": 1e-08,
	"qk_scale_factor": 3.87,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"rope_theta": 500000.0,
	"rope_type": "default"
	},
	"sliding_window": 2048,
	"tie_word_embeddings": false,
	"use_cache": true,
	"vocab_size": 202048
	},
	"transformers_version": "5.15.0.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_glimmer_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": 10000.0,
	"rope_type": "default"
	}
	}
	}