Transformers documentation

Muse Spark Açık

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

Bu model, 2026-10-14 tarihinde Hugging Face Transformers'a katkıda bulunulmuştur.

Muse Spark Açık

Genel Bakış

Muse Spark Open, Meta tarafından geliştirilen, metin, görsel, ses ve video girdilerini kabul edip metin üreten çok modlu bir uzman karışımı (MoE) modelidir. Toplam 816 milyar parametreye sahip olup token başına 42 milyar aktif parametre kullanır ve tüm girdi modları arasında paylaşılan, 1.048.576 tokene kadar uzanan bir bağlam penceresi destekler. Model, çoklu dosya kod düzenleme, hata ayıklama ve araç kullanımı dahil olmak üzere ajan tabanlı kodlama görevleri için eğitilmiştir.

Dil omurgası, her biri jetonları 256 uzman arasından 8'ine yönlendiren 62 transformer katmanından oluşur. Gruplu sorgu dikkati, sorgu-anahtar normalizasyonu, dikkat çıktısı kapılaması ve normalizasyonu ile öğrenilmiş artı kapıları kullanır. Ortak bir algı kodlayıcı görüntüleri ve video karelerini işlerken, konvolüsyonel ses kodlayıcı saniyede 12,5 jeton hızında ses temsilleri üretir. Muse Spark Open, çok modlu girdiler için sohbet şablonunda yapılan genişletmelerle birlikte Muse Glimmer ile tokenizörünü ve sözlüğünü paylaşır. Kontrol noktaları BF16 ve NVFP4 biçimlerinde mevcuttur.

Kaynaklar

AutoModel

AutoModel Görüntü

AutoModel Video

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|>

NVFP4 Ağırlıkları

Daha düşük bellek gereksinimlerine sahip NVFP4 kuantize ağırlıklar hub'da mevcuttur. Model, kodda herhangi bir değişiklik yapılmadan herhangi bir NVFP4 uyumlu cihazda yüklenebilir. Kuantizasyon yapılandırması, yükleme sırasında otomatik olarak uygulanır.

NVFP4 desteği için transformers, bu dal üzerinden kurulmalıdır.
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 Açık

Genel Bakış

Kaynaklar

NVFP4 Ağırlıkları

MuseSparkConfig

sınıf transformers.MuseSparkConfig

MuseSparkTextConfig

sınıf transformers.MuseSparkTextConfig

MuseSparkVisionConfig

sınıf transformers.MuseSparkVisionConfig

MuseSparkAudioConfig

sınıf transformers.MuseSparkAudioConfig

MuseSparkFeatureExtractor

sınıf transformers.MuseSparkFeatureExtractor

MuseSparkProcessor

sınıf transformers.MuseSparkProcessor

MuseSparkPreTrainedModel

sınıf transformers.MuseSparkPreTrainedModel

MuseSparkTextModel

sınıf transformers.MuseSparkTextModel

forward

MuseSparkVisionModel

sınıf transformers.MuseSparkVisionModel

forward

MuseSparkAudioModel

sınıf transformers.MuseSparkAudioModel

forward

MuseSparkModel

sınıf transformers.MuseSparkModel

forward

MuseSparkForConditionalGeneration

sınıf transformers.MuseSparkForConditionalGeneration

forward