Instructions to use ryanontheinside/rap-acestep1.5-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ryanontheinside/rap-acestep1.5-v1 with PEFT:
Task type is invalid.
- ACE-Step
How to use ryanontheinside/rap-acestep1.5-v1 with ACE-Step:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
Rap
Rap-style generation. Covers: modern hip-hop track, deep 808 bass, rapid hi-hat rolls, melodic flow, atmospheric pads; west coast hip-hop, smooth bassline, jazzy keys, laid-back flow; and trap rap track, aggressive hi-hats, dark synth pads, heavy 808s.
Quick start
- Base model: AceStep v1.5 Turbo (2B)
- Trigger word:
roti-r4pz(must appear in the prompt to activate) - Recommended strength: 1.0
- Tested strength range: 0.3 โ 1.5
- Recommended steps: 8
- Recommended guidance: 7.0
- Recommended shift: 3.0
- Sample rate: 48000 Hz
Example prompts
modern hip-hop track, deep 808 bass, rapid hi-hat rolls, melodic flow, atmospheric pads(140 BPM, F minor)west coast hip-hop, smooth bassline, jazzy keys, laid-back flow(90 BPM, G minor)trap rap track, aggressive hi-hats, dark synth pads, heavy 808s(145 BPM, D minor)
Training
- Rank 64, alpha 128, dropout 0.1
- Target modules: q_proj, k_proj, v_proj, o_proj
- 500 epochs / 7500 steps, batch 1, optimizer adamw_fused, lr 0.0003, warmup 100
- Dataset: 12 synthetic tracks, 2921s total, instrumental fraction 0.083
Files
rap-v1.safetensorsโ PEFT LoRA weights (88,130,248 bytes, sha256d00a0f7125d657dbc09814e0d017b585d03fd93249b8cd63faff84e7e625bfc4)rap-v1.metadata.jsonโ machine-readable sidecar (schema v1)adapter_config.jsonโ PEFT adapter config
Full metadata: see rap-v1.metadata.json.
- Downloads last month
- 15