Instructions to use darkc0de/Muse-Glimmer-30B-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use darkc0de/Muse-Glimmer-30B-heretic with Transformers:

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

pipe = pipeline("image-text-to-text", model="darkc0de/Muse-Glimmer-30B-heretic")
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("darkc0de/Muse-Glimmer-30B-heretic")
model = AutoModelForMultimodalLM.from_pretrained("darkc0de/Muse-Glimmer-30B-heretic", 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 darkc0de/Muse-Glimmer-30B-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "darkc0de/Muse-Glimmer-30B-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "darkc0de/Muse-Glimmer-30B-heretic",
		"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/darkc0de/Muse-Glimmer-30B-heretic

SGLang

How to use darkc0de/Muse-Glimmer-30B-heretic 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 "darkc0de/Muse-Glimmer-30B-heretic" \
    --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": "darkc0de/Muse-Glimmer-30B-heretic",
		"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 "darkc0de/Muse-Glimmer-30B-heretic" \
        --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": "darkc0de/Muse-Glimmer-30B-heretic",
		"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 darkc0de/Muse-Glimmer-30B-heretic with Docker Model Runner:
```
docker model run hf.co/darkc0de/Muse-Glimmer-30B-heretic
```

DFlash & mmproj question

by DzmitryTheOtherOne - opened Aug 14

Discussion

DzmitryTheOtherOne

Aug 14

Hello,

Would the original DFlash file from Meta (https://huggingface.co/meta-models/Muse-Glimmer-30B-GGUF/blob/main/dflash-Muse-Glimmer-30B-Q4_K_M.gguf) work with this heretic version?

Thanks!

DzmitryTheOtherOne

Aug 14

•

edited Aug 14

Same question in regards to the mmproj file (https://huggingface.co/meta-models/Muse-Glimmer-30B-GGUF/blob/main/mmproj-Muse-Glimmer-30B-Q4_K_M.gguf)? 😃

DzmitryTheOtherOne changed discussion title from DFlash module to DFlash & mmproj question Aug 14

nikich340

28 days ago

Hello,

Would the original DFlash file from Meta (https://huggingface.co/meta-models/Muse-Glimmer-30B-GGUF/blob/main/dflash-Muse-Glimmer-30B-Q4_K_M.gguf) work with this heretic version?

Thanks!

I think you could try and check if generate speed actually improves (try with draft n max = 1 and 2), but remember that prefill speed may slightly reduce.
mmproj files usually are not touched by heretic process, so you can use original mmproj quants without problems.

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