Instructions to use mlasli/Muse-Glimmer-30B-Abliterated-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlasli/Muse-Glimmer-30B-Abliterated-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="mlasli/Muse-Glimmer-30B-Abliterated-BF16")
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("mlasli/Muse-Glimmer-30B-Abliterated-BF16")
model = AutoModelForMultimodalLM.from_pretrained("mlasli/Muse-Glimmer-30B-Abliterated-BF16", 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 mlasli/Muse-Glimmer-30B-Abliterated-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlasli/Muse-Glimmer-30B-Abliterated-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlasli/Muse-Glimmer-30B-Abliterated-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlasli/Muse-Glimmer-30B-Abliterated-BF16

SGLang

How to use mlasli/Muse-Glimmer-30B-Abliterated-BF16 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 "mlasli/Muse-Glimmer-30B-Abliterated-BF16" \
    --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": "mlasli/Muse-Glimmer-30B-Abliterated-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "mlasli/Muse-Glimmer-30B-Abliterated-BF16" \
        --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": "mlasli/Muse-Glimmer-30B-Abliterated-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mlasli/Muse-Glimmer-30B-Abliterated-BF16 with Docker Model Runner:
```
docker model run hf.co/mlasli/Muse-Glimmer-30B-Abliterated-BF16
```

mlasli commited on about 17 hours ago

Commit

b01562a

verified ·

1 Parent(s): 0354459

Add model card with abliteration details

Browse files

Files changed (1) hide show

README.md +57 -0

README.md ADDED Viewed

	@@ -0,0 +1,57 @@

+---
+license: apache-2.0
+library_name: transformers
+tags:
+- abliterated
+- muse
+- glimmer
+- uncensored
+- vision-language-model
+base_model: meta-models/Muse-Glimmer-30B
+---
+# Muse Glimmer 30B Abliterated (BF16)
+Uncensored version of Meta's **Muse Glimmer 30B** — a 30B parameter vision-language model.
+**Abliteration**: Weight-level refusal direction subtraction using an ErisForge-style algorithm.
+## Details
+| Metric | Value |
+|--------|-------|
+| **Base Model** | meta-models/Muse-Glimmer-30B |
+| **Method** | ErisForge-style weight modification |
+| **Architecture** | MuseGlimmerForConditionalGeneration |
+| **Refusal Layer** | 33/52 (65% depth) |
+| **Harmful/Harmless Pairs** | 256 each |
+| **Separation Score** | 86.34 |
+| **Refusal Reduction** | ~50% |
+## Usage
+```python
+from transformers import AutoModelForImageTextToText, AutoTokenizer
+model = AutoModelForImageTextToText.from_pretrained(
+    "mlasli/Muse-Glimmer-30B-Abliterated-BF16",
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(
+    "mlasli/Muse-Glimmer-30B-Abliterated-BF16",
+    trust_remote_code=True
+)
+```
+## Quantized Versions (GGUF)
+| Quant | Size | Repo |
+|-------|------|------|
+| Q4_K_M | ~16 GB | [Q4_K_M](https://huggingface.co/mlasli/Muse-Glimmer-30B-Abliterated-Q4_K_M-GGUF) |
+| Q6_K | ~22 GB | [Q6_K](https://huggingface.co/mlasli/Muse-Glimmer-30B-Abliterated-Q6_K-GGUF) |
+| Q8_0 | ~28 GB | [Q8_0](https://huggingface.co/mlasli/Muse-Glimmer-30B-Abliterated-Q8_0-GGUF) |
+## License
+Apache 2.0 — same as the original Meta license.
+## Disclaimer
+This model has been modified to reduce refusal behavior. Use responsibly.