Instructions to use coder3101/Muse-Glimmer-30B-heretic-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use coder3101/Muse-Glimmer-30B-heretic-v2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="coder3101/Muse-Glimmer-30B-heretic-v2")
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("coder3101/Muse-Glimmer-30B-heretic-v2")
model = AutoModelForMultimodalLM.from_pretrained("coder3101/Muse-Glimmer-30B-heretic-v2", 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 coder3101/Muse-Glimmer-30B-heretic-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "coder3101/Muse-Glimmer-30B-heretic-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "coder3101/Muse-Glimmer-30B-heretic-v2",
		"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/coder3101/Muse-Glimmer-30B-heretic-v2

SGLang

How to use coder3101/Muse-Glimmer-30B-heretic-v2 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 "coder3101/Muse-Glimmer-30B-heretic-v2" \
    --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": "coder3101/Muse-Glimmer-30B-heretic-v2",
		"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 "coder3101/Muse-Glimmer-30B-heretic-v2" \
        --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": "coder3101/Muse-Glimmer-30B-heretic-v2",
		"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 coder3101/Muse-Glimmer-30B-heretic-v2 with Docker Model Runner:
```
docker model run hf.co/coder3101/Muse-Glimmer-30B-heretic-v2
```

coder3101 commited on Aug 16

Commit

e10702b

verified ·

1 Parent(s): f2d1abf

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +9 -11

README.md CHANGED Viewed

@@ -8,8 +8,6 @@ tags:
 - decensored
 - abliterated
 - ara
-base_model:
-- meta-models/Muse-Glimmer-30B
 ---
 # This is a decensored version of [meta-models/Muse-Glimmer-30B](https://huggingface.co/meta-models/Muse-Glimmer-30B), made using [Heretic](https://github.com/p-e-w/heretic) v1.2.0 with the [Arbitrary-Rank Ablation (ARA)](https://github.com/p-e-w/heretic/pull/211) method (with row-norm preservation)
@@ -17,19 +15,19 @@ base_model:
 | Parameter | Value |
 | :-------- | :---: |
-| **start_layer_index** | 10 |
-| **end_layer_index** | 50 |
-| **preserve_good_behavior_weight** | 0.5826 |
-| **steer_bad_behavior_weight** | 0.0008 |
-| **overcorrect_relative_weight** | 0.9762 |
-| **neighbor_count** | 5 |
 ## Performance
 | Metric | This model | Original model ([meta-models/Muse-Glimmer-30B](https://huggingface.co/meta-models/Muse-Glimmer-30B)) |
 | :----- | :--------: | :---------------------------: |
-| **KL divergence** | 0.3339 | 0 *(by definition)* |
-| **Refusals** | 9/100 | 60/100 |
 -----
@@ -244,4 +242,4 @@ All artifacts are released under Apache 2.0:
 | DFlash drafter head | Speculative decoding companion for faster generation |
 | Perception encoder | Frozen ViT-G/14 vision encoder (\~1.8B params) |
-**Where to send questions or comments about the model:** Please provide any feedback, comments or bug reports on the model through the Hugging Face page at [https://huggingface.co/meta-models/](https://huggingface.co/meta-models/). For more technical information about generation parameters and recipes for how to use Muse Glimmer in applications, please see the developer documentation.

 - decensored
 - abliterated
 - ara
 ---
 # This is a decensored version of [meta-models/Muse-Glimmer-30B](https://huggingface.co/meta-models/Muse-Glimmer-30B), made using [Heretic](https://github.com/p-e-w/heretic) v1.2.0 with the [Arbitrary-Rank Ablation (ARA)](https://github.com/p-e-w/heretic/pull/211) method (with row-norm preservation)
 | Parameter | Value |
 | :-------- | :---: |
+| **start_layer_index** | 15 |
+| **end_layer_index** | 45 |
+| **preserve_good_behavior_weight** | 0.5532 |
+| **steer_bad_behavior_weight** | 0.0004 |
+| **overcorrect_relative_weight** | 0.9319 |
+| **neighbor_count** | 15 |
 ## Performance
 | Metric | This model | Original model ([meta-models/Muse-Glimmer-30B](https://huggingface.co/meta-models/Muse-Glimmer-30B)) |
 | :----- | :--------: | :---------------------------: |
+| **KL divergence** | 0.1683 | 0 *(by definition)* |
+| **Refusals** | 14/100 | 58/100 |
 -----
 | DFlash drafter head | Speculative decoding companion for faster generation |
 | Perception encoder | Frozen ViT-G/14 vision encoder (\~1.8B params) |
+**Where to send questions or comments about the model:** Please provide any feedback, comments or bug reports on the model through the Hugging Face page at [https://huggingface.co/meta-models/](https://huggingface.co/meta-models/). For more technical information about generation parameters and recipes for how to use Muse Glimmer in applications, please see the developer documentation.