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 / config.json

mgaruccio

GPTQ Int4 G128 DFlash assistant

8a61e51 verified about 1 month ago

Raw History Blame Contribute Delete

2.33 kB

	{
	"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,
	"quantization_config": {
	"bits": 4,
	"checkpoint_format": "gptq",
	"desc_act": false,
	"format": "gptq",
	"group_size": 128,
	"lm_head": false,
	"meta": {
	"act_group_aware": true,
	"auto_forward_data_parallel": true,
	"damp_auto_increment": 0.01,
	"damp_percent": 0.05,
	"dense_vram_strategy": "exclusive",
	"dense_vram_strategy_devices": null,
	"fallback": {
	"smooth": null,
	"strategy": "rtn",
	"threshold": "0.5%"
	},
	"foem": null,
	"gc_mode": "interval",
	"gptaq": null,
	"hessian": {
	"chunk_bytes": null,
	"chunk_size": null,
	"staging_dtype": "float32"
	},
	"mock_quantization": false,
	"moe_vram_strategy": "exclusive",
	"moe_vram_strategy_devices": null,
	"mse": 0.0,
	"offload_to_disk": true,
	"offload_to_disk_path": "/tmp/muse-dflash-assistant-gptq-offload",
	"pack_impl": "cpu",
	"quantizer": [
	"gptqmodel:7.3.2"
	],
	"static_groups": false,
	"true_sequential": true,
	"uri": "https://github.com/modelcloud/gptqmodel",
	"wait_for_submodule_finalizers": false
	},
	"method": "gptq",
	"modules_in_block_to_quantize": [
	"self_attn.qkv_proj",
	"self_attn.o_proj",
	"mlp.gate_up_proj",
	"mlp.down_proj"
	],
	"pack_dtype": "int32",
	"quant_method": "gptq",
	"sym": true
	},
	"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": "5.15.1",
	"use_cache": false
	}