Store › model › Embeddings
SheetSage2-GGUF
by audio-cpp · source Hugging Face · updated 2026-09-13
cc-by-nc-4.02.5 GB~4 GB RAMsource aliveunlabeled
GGUF conversion of m-a-p/SheetSage2 for audio.cpp. SheetSage2 transcribes music into melody, chords, beats, key, structure, and editable scores. This is a converted checkpoint, not a new model or an…
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:audio-cpp/SheetSage2-GGUF and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/audio-cpp/SheetSage2-GGUF
- License: cc-by-nc-4.0 (restricted license: terms at the source apply)
- Requirements: about 4 GB of RAM, 2.5 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp.
- Tags:
transformersggufsheetsage2audiomusicmusic-transcriptionmidiabc-notationcustom_codefeature-extractionendpoints_compatible
Numbers
- 21,411 downloads on Hugging Face
- 8 likes
- license cc-by-nc-4.0
- 2.5 GB for sheetsage2-orig.gguf
- 327,838 npm downloads a week for node-llama-cpp
- latest node-llama-cpp@3.22.1
Numbers as of 2026-10-02 20:59 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
sheetsage2-orig.gguf | 2.5 GB |
From the source README
SheetSage2-GGUF
GGUF conversion of m-a-p/SheetSage2 for audio.cpp. SheetSage2 transcribes music into melody, chords, beats, key, structure, and editable scores. This is a converted checkpoint, not a new model or an official upstream release.
Demo
Watch or download the demo.
Upstream
- SheetSage2: pinned revision eab522a8168e8b8b8c4856bf8609cd86198f01fe.
- Backbone: m-a-p/MERT-v2-FullSong.
- SheetSage2 source safetensors SHA256: `b235f68091a5f5b644000f2b5acb57d1e70432aca2b34ab1b9cf27236e1f4274`.
- Backbone source safetensors SHA256: `e6dd2ab187d6dd62b6521cd7d8f932e237acf0c5757745a7232082e28391350d`.
The packaged file uses the audio.cpp SheetSage2 runtime, not the upstream Transformers loader.
Weights and Size
| File | Storage | Size |
|---|---|---|
| `sheetsage2-orig.gguf` | Unquantized FP32, merged model | 2,708,224,512 bytes (2.71 GB / 2.52 GiB) |
The upstream `model.safetensors` is only 228,738,564 bytes (228.74 MB): it contains SheetSage2 adapters and task-specific weights and relies on the separately downloaded MERT-v2-FullSong backbone. The GGUF includes that backbone with the LoRA updates already merged, plus the task weights and embedded configuration. No separate backbone checkpoint is needed at inference time.
The merged GGUF stores 677,020,953 FP32 values across 1,039 tensors. The larger size comes from packaging the complete merged model, not GGUF container overhead or accidental duplication. Both the upstream SheetSage2 safetensors and this GGUF use FP32; this is not an FP16-to-FP32 size increase.
Conversion Validation
Card id model:hf:audio-cpp/SheetSage2-GGUF · collected 2026-10-02 20:59 UTC · JSON