Instructions to use mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128 with Transformers:

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

pipe = pipeline("text-generation", model="mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128")
model = AutoModel.from_pretrained("mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128

SGLang

How to use mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128 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 "mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128" \
    --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": "mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128",
		"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 "mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128" \
        --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": "mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128 with Docker Model Runner:
```
docker model run hf.co/mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128
```

Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128 / model.safetensors

mgaruccio

GPTQ Int4 G128 DFlash assistant

8a61e51 verified about 1 month ago

History Blame Contribute Delete

1.66 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 4020b5800493d64ebd4e2a9e3a27859e16d95c3a760cc2c1df29b23491789a53
Size of remote file:: 1.66 GB
SHA256:: 25ab1e1d04508159b44b833c31b1f74625bc1dc0486d6a9fcaeead577091fcee

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.