Downloads · 30 days
4
7% of all-time downloads
affectscore-ace-step-r64-20260629
HiiragiLee/affectscore-ace-step-r64-20260629
affectscore-ace-step-r64-20260629 is a machine learning model from HiiragiLee. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.
LoRA adapter for ACE-Step v1 3.5B from the AffectScore rank sweep (r ∈ {16, 32, 64}). This checkpoint diverged at epoch 40 following a gradient spike caused by Q2-weighted sampling concentrating the 34 available Q2 cl…
All-time downloads
59
Public
Repo size
62.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors62.9 MB · 100%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Jun 30, 2026
- Updated
- Aug 7, 2026
- SHA
- 8af1cdef
Base models
Model card
From the Hugging Face model README
AffectScore -- LoRA r=64 (diverged -- not recommended)
LoRA adapter for ACE-Step v1 3.5B from the AffectScore rank sweep (r ∈ {16, 32, 64}). This checkpoint diverged at epoch 40 following a gradient spike caused by Q2-weighted sampling concentrating the 34 available Q2 clips into consecutive batches. It is provided for reproducibility only. Use r=32 instead.
Code and Colab notebooks: github.com/LeeTgk/affectscore (link active after publication)
Training
| Parameter | Value |
|---|---|
| Base model | ACE-Step/ACE-Step-v1-3.5B |
| LoRA rank | 64 |
| LoRA targets | cross_attn.q_proj, cross_attn.v_proj |
| use_rslora | True |
| lora_dropout | 0.05 |
| Training clips | 1,571 (CC0/CC-BY, CLAP-quality filtered) |
| Epochs | 50 (diverged at epoch 40) |
| Learning rate | 1e-4 |
| Batch size | 8 |
| Hardware | NVIDIA A100 (Google Colab) |
Training dataset: https://zenodo.org/records/21830658
Ablation variants
See affectscore-ace-step-r32-20260629 for full model details, evaluation results, and the complete variant table.
Citation
Citation will be added once the paper is published. If you use this model before then, please link to this repository.
- Library
- peft
- License
- mit
- Created
- Jun 30, 2026
- Updated
- Aug 7, 2026