Downloads · 30 days
5
8% of all-time downloads
Qwen3-4B-GiantMIDI-REMI
sullivanUCSD/Qwen3-4B-GiantMIDI-REMI
Qwen3-4B-GiantMIDI-REMI is a machine learning model from sullivanUCSD. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Qwen3-4B adapted to symbolic piano generation on GiantMIDI-Piano, with the LoRA adapters and the 316 new REMI music-token embeddings merged into the full weights. This is the "out-of-domain pretraining" arm of a CSE 2…
All-time downloads
66
Public
Parameters
4B
8.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- May 28, 2026
- Updated
- May 28, 2026
- SHA
- 6414c633
Base models
Model card
From the Hugging Face model README
Qwen3-4B-GiantMIDI-REMI
Qwen3-4B adapted to symbolic piano generation on GiantMIDI-Piano, with the LoRA adapters and the 316 new REMI music-token embeddings merged into the full weights. This is the "out-of-domain pretraining" arm of a CSE 253 (UCSD) study on whether pretraining domain or scale matters more for symbolic music.
What was trained
The text base never saw music. We added the 316 REMI tokens (<MIDI_TOK_0..315>)
as special tokens, froze the base in 4-bit, and trained LoRA (r=16) plus only the
316 new embedding rows. The full bf16 weights here are the merged result.
Usage
The tokenizer includes the 316 <MIDI_TOK_i> tokens, each mapping 1:1 to a
MidiTok REMI id (316-token REMI vocabulary). Generation is constrained to those
tokens, then decoded to MIDI with MidiTok.
Results (test set, REMI vocabulary)
Perplexity 13.55, pitch KL 0.49, interval KL 0.51, repetition 0.022, 0% invalid.
Base model: Qwen/Qwen3-4B (Apache-2.0). Coursework artifact.
- Type
- qwen3
- License
- apache-2.0
- Created
- May 28, 2026
- Updated
- May 28, 2026