Text-to-Audio
Transformers
Safetensors
ACE-Step
feature-extraction
ace-step
text-to-music
music-generation
bf16
bfloat16
custom_code
Instructions to use Chillarmo/acestep-v15-xl-base-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Chillarmo/acestep-v15-xl-base-bf16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="Chillarmo/acestep-v15-xl-base-bf16", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Chillarmo/acestep-v15-xl-base-bf16", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
ACE-Step 1.5 XL Base BF16
This repository contains a BF16 safetensors package of ACE-Step/acestep-v15-xl-base.
It keeps the standard ACE-Step / Transformers AutoModel.from_pretrained(..., trust_remote_code=True)
layout and does not require Optimum Quanto or any custom quantization loader.
Files
model-00001-of-00004.safetensorsthroughmodel-00004-of-00004.safetensors- BF16 model shardsmodel.safetensors.index.json- shard indexconfig.jsonand ACE-Step custom model codesilence_latent.pt- ACE-Step sidecar tensor from the source repobf16_summary.json- conversion metadata
Load
from transformers import AutoModel
model = AutoModel.from_pretrained(
"./acestep-v15-xl-base-bf16",
trust_remote_code=True,
attn_implementation="sdpa",
dtype="auto",
)
model.eval()
- Downloads last month
- 9
Model tree for Chillarmo/acestep-v15-xl-base-bf16
Base model
ACE-Step/acestep-v15-xl-base