Transformers documentation

Muse Spark Aberto

Transformers

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v5.22.1).

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

Este modelo foi contribuído para o Hugging Face Transformers em 2026-10-14.

Muse Spark Aberto

Visão geral

Muse Spark Open é um modelo multimodal de mistura de especialistas (MoE) desenvolvido pela Meta que aceita texto, imagens, áudio e vídeo como entrada e gera texto. Ele possui 816 bilhões de parâmetros no total, com 42 bilhões ativos por token, e suporta uma janela de contexto de até 1.048.576 tokens compartilhados entre todas as modalidades de entrada. O modelo é treinado para tarefas de codificação agêntica, incluindo edição de código em múltiplos arquivos, depuração e uso de ferramentas.

O backbone de linguagem consiste em 62 camadas de transformer, cada uma roteando tokens para 8 de 256 especialistas. Ele utiliza atenção de consulta agrupada com normalização de consulta-chave, portão e normalização da saída da atenção, e portões residuais aprendidos. Um codificador de percepção compartilhado processa imagens e quadros de vídeo, enquanto um codificador de áudio convolucional produz representações de áudio a 12,5 tokens por segundo. O Muse Spark Open compartilha seu tokenizador e vocabulário com o Muse Glimmer, com extensões no modelo de chat para entradas multimodais. Os checkpoints estão disponíveis nos formatos BF16 e NVFP4.

Recursos

AutoModel

AutoModel Image

AutoModel Vídeo

AutoModel Audio

import os

from transformers import AutoModelForMultimodalLM, AutoProcessor, DistributedConfig

distributed_config = DistributedConfig(
    tp_size=int(os.environ["WORLD_SIZE"]), # Number of devices across which the dense layers are sharded
    ep_size=int(os.environ["WORLD_SIZE"]), # Number of devices across which the experts are distributed
)

processor = AutoProcessor.from_pretrained("meta-models/Muse-Spark-Open-816B-A42B")
model = AutoModelForMultimodalLM.from_pretrained(
    "meta-models/Muse-Spark-Open-816B-A42B",
    distributed_config=distributed_config,
)

messages = [
    {"role": "user", "content": "Explain in one sentence why the sky is usually blue."},
]
inputs = processor.apply_chat_template(
    messages,
    reasoning_effort="low",  # default: xhigh, options: low/medium/high/xhigh
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device).to(model.dtype)
input_len = inputs["input_ids"].shape[-1]

outputs = model.generate(**inputs, max_new_tokens=512)
print(processor.decode(outputs[0][input_len:], skip_special_tokens=False))
#  to=self<|message|>Explain in one sentence why the sky is usually blue.
# ...
# <|eom|><|start|>assistant to=user<|message|>The sky is usually blue because molecules in Earth's atmosphere scatter shorter-wavelength blue sunlight in all directions much more strongly than longer-wavelength red light.<|eot|>

import os

from transformers import AutoModelForMultimodalLM, AutoProcessor, DistributedConfig

distributed_config = DistributedConfig(
    tp_size=int(os.environ["WORLD_SIZE"]),
    ep_size=int(os.environ["WORLD_SIZE"]),
)

processor = AutoProcessor.from_pretrained("meta-models/Muse-Spark-Open-816B-A42B")
model = AutoModelForMultimodalLM.from_pretrained(
    "meta-models/Muse-Spark-Open-816B-A42B",
    distributed_config=distributed_config,
)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            {"type": "text", "text": "What is shown in this image?"},
        ],
    },
]
inputs = processor.apply_chat_template(
    messages,
    reasoning_effort="medium", # default: xhigh, options: low/medium/high/xhigh
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device).to(model.dtype)
input_len = inputs["input_ids"].shape[-1]

outputs = model.generate(**inputs, max_new_tokens=512)
response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
print(response)
#  to=self<|message|>What is shown in this image?
# ...
# <|eom|><|start|>assistant to=user<|message|>The image shows a **Pallas's cat — also known as a manul, *Otocolobus manul*** — walking through snow.
#
# It is a small, stocky wild cat recognizable by:
#
# * **Its extremely dense, long, greyish-brown winter coat** with faint dark stripes and a dusting of snow on its back
# * **Its flat, broad face** with low-set ears, a short muzzle, and dark stripes on the cheeks
# * **Its short legs and thick, plump body** adapted for cold climates
#
# The cat is captured mid-stride on a snow-covered surface, with one front paw lifted. In the background are white birch tree trunks with black markings and a chain-link fence on the left, indicating the animal is in a zoo or wildlife enclosure in winter.<|eot|>

import os

from transformers import AutoModelForMultimodalLM, AutoProcessor, DistributedConfig

distributed_config = DistributedConfig(
    tp_size=int(os.environ["WORLD_SIZE"]),
    ep_size=int(os.environ["WORLD_SIZE"]),
)

processor = AutoProcessor.from_pretrained("meta-models/Muse-Spark-Open-816B-A42B")
model = AutoModelForMultimodalLM.from_pretrained(
    "meta-models/Muse-Spark-Open-816B-A42B",
    distributed_config=distributed_config,
)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "video", "url": "https://huggingface.co/datasets/hf-internal-testing/fixtures_videos/resolve/main/tennis.mp4"},
            {"type": "text", "text": "What is happening in this video?"},
        ],
    },
]
inputs = processor.apply_chat_template(
    messages,
    reasoning_effort="medium",  # default: xhigh, options: low/medium/high/xhigh
    processor_kwargs={
        "fps": 2,   # default: 2, number of frames sampled per second
        "num_frames": 8, # default: 94, maximum number of frames sampled from the video
    },
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device).to(model.dtype)
input_len = inputs["input_ids"].shape[-1]

outputs = model.generate(**inputs, max_new_tokens=512)
print(processor.decode(outputs[0][input_len:], skip_special_tokens=False))
#  to=self<|message|>What is happening in this video?
# ...
# <|eom|><|start|>assistant to=user<|message|>In this video two people are playing tennis on an indoor court.
#
# The shot is taken from behind one of the players - a man in a white t-shirt, black shorts and white shoes and socks. He is standing near the baseline on an orange hard court with white lines, in a ready position with his knees bent and his racket held in front of him.
#
# Across the net, on the far side of the court, is his opponent, also dressed in light-colored clothing.
#
# The sequence shows a short rally:
#
# *   The opponent hits the ball over the net.
# *   The man in the foreground shuffles to his left, turns his body, and prepares for a shot.
# *   He executes a two-handed backhand, swinging the racket across his body and following through as he hits the ball back over the net.
#
# The setting is a large indoor tennis hall with a high, arched ceiling with exposed wooden beams and overhead fluorescent lights. The court is surrounded by a grey run-off area, green windscreening on the walls, and netting that separates it from adjacent courts. On the right side you can see an umpire's chair and a few yellow and black benches. An "Adobe Stock" watermark is visible in the center of the frame.<|eot|>

Pesos NVFP4

Os pesos quantizados em NVFP4 com requisitos de memória reduzidos estão disponíveis no hub. O modelo pode ser carregado em qualquer dispositivo compatível com NVFP4 sem alterações no código. A configuração de quantização é aplicada automaticamente no momento do carregamento.

Para suporte a NVFP4, o transformers deve ser instalado a partir desta branch.
pip install git+https://github.com/huggingface/transformers.git@finegrained-per-scheme-demo

import os

from transformers import AutoModelForMultimodalLM, AutoProcessor, DistributedConfig

distributed_config = DistributedConfig(
    tp_size=int(os.environ["WORLD_SIZE"]),
    ep_size=int(os.environ["WORLD_SIZE"]),
)

processor = AutoProcessor.from_pretrained("meta-models/Muse-Spark-Open-816B-A42B-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained(
    "meta-models/Muse-Spark-Open-816B-A42B-NVFP4",
    distributed_config=distributed_config,
)

# ...

Transformers

Muse Spark Aberto

Visão geral

Recursos

Pesos NVFP4

MuseSparkConfig

classe transformers.MuseSparkConfig

MuseSparkTextConfig

classe transformers.MuseSparkTextConfig

MuseSparkVisionConfig

classe transformers.MuseSparkVisionConfig

MuseSparkAudioConfig

classe transformers.MuseSparkAudioConfig

MuseSparkFeatureExtractor

classe transformers.MuseSparkFeatureExtractor

MuseSparkProcessor

classe transformers.MuseSparkProcessor

MuseSparkPreTrainedModel

classe transformers.MuseSparkPreTrainedModel

MuseSparkTextModel

classe transformers.MuseSparkTextModel

forward

MuseSparkVisionModel

classe transformers.MuseSparkVisionModel

forward

MuseSparkAudioModel

classe transformers.MuseSparkAudioModel

forward

MuseSparkModel

classe transformers.MuseSparkModel

forward

MuseSparkForConditionalGeneration

classe transformers.MuseSparkForConditionalGeneration

forward