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

Libraries

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

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

pipe = pipeline("image-text-to-text", model="ArchiveStudio/Muse-Glimmer-30B-assistant")

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("ArchiveStudio/Muse-Glimmer-30B-assistant")
model = AutoModel.from_pretrained("ArchiveStudio/Muse-Glimmer-30B-assistant", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArchiveStudio/Muse-Glimmer-30B-assistant"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArchiveStudio/Muse-Glimmer-30B-assistant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ArchiveStudio/Muse-Glimmer-30B-assistant

SGLang

How to use ArchiveStudio/Muse-Glimmer-30B-assistant 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 "ArchiveStudio/Muse-Glimmer-30B-assistant" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArchiveStudio/Muse-Glimmer-30B-assistant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ArchiveStudio/Muse-Glimmer-30B-assistant" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArchiveStudio/Muse-Glimmer-30B-assistant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

Muse-Glimmer-30B-assistant / config.json

ArchiveStudio

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

2a58ddf 10 days ago

Raw

History Blame Contribute Delete

883 Bytes

	{
	"architectures": [
	"MuseGlimmerAssistantModel"
	],
	"attention_dropout": 0,
	"block_size": 16,
	"bos_token_id": 200000,
	"dtype": "bfloat16",
	"eos_token_id": 200001,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 6656,
	"intermediate_size": 19968,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention"
	],
	"mask_token_id": 201818,
	"max_position_embeddings": 131072,
	"model_type": "muse_glimmer_assistant",
	"num_attention_heads": 32,
	"num_hidden_layers": 5,
	"num_key_value_heads": 8,
	"pad_token_id": 200018,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"rope_theta": 500000.0,
	"rope_type": "default"
	},
	"sliding_window": 2048,
	"target_layer_ids": [
	1,
	13,
	25,
	37,
	49
	],
	"transformers_version": "5.15.0.dev0"
	}