Buckets:
2.85 GB
9 files
Updated 16 days ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| onnx | 2 items | ||
| .gitattributes | 1.57 kB xet | 9b755628 | |
| README.md | 1.41 kB xet | 369f1e53 | |
| config.json | 1.73 kB xet | 698fe818 | |
| generation_config.json | 69 Bytes xet | f39b4ec6 | |
| model.safetensors | 933 MB xet | 8fa5069f | |
| pytorch_model.bin | 933 MB xet | 541add60 | |
| soundfont.sf2 | 51.3 MB xet | 7d5b4f90 |
Model Card for midi-model
Midi event transformer for music generation
Model Updates
- tv2o-medium model: MidiTokenizerV2. skytnt/midi-model-tv2o-medium
- v1.2 : Optimise the tokenizer and dataset. The dataset was filtered by MIDITokenizer.check_quality. Using the higher quality dataset to train the model, the performance of the model is significantly improved.
Model Details
Model Description
- Developed by: SkyTNT
- Model type: Transformer
- License: apache-2.0
Model Sources
- Repository: https://github.com/SkyTNT/midi-model
- Demo: https://huggingface.co/spaces/skytnt/midi-composer
Training Details
Training Data
Training Hyperparameters
- basemodel: v1.1
- lr: 1e-4
- weight-decay: 0.01
- batch: 2x2x2
- fp16 mixed precision
Loss
- val loss: 0.238
Files
- model.ckpt: latest model checkpoint
- soundfont.sf2: soundfont file, i put it here for convenient downloading , source
- onnx/*.onnx: onnx format model
- Total size
- 2.85 GB
- Files
- 9
- Last updated
- Nov 3
- Pre-warmed CDN
- US EU US EU