loubb commited on
Commit
e27d9df
Β·
verified Β·
1 Parent(s): 33d53a4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -13,10 +13,10 @@ tags:
13
 
14
  `Aria` is a pretrained autoregressive generative model for symbolic music based on the LLaMA 3.2 (1B) architecture. It was trained on ~60k hours of MIDI transcriptions of expressive solo-piano recordings. It has been finetuned to produce realistic continuations of solo-piano compositions as well as to produce general-purpose contrastive MIDI embeddings.
15
 
16
- This HuggingFace page contains weights and usage instructions for the pretrained base model. For the generative model, see [aria-medium-gen](https://huggingface.co/loubb/aria-medium-gen), and for the embedding model, see [aria-medium-embedding](https://huggingface.co/loubb/aria-medium-embedding).
17
 
18
 
19
- πŸ“– Read our [release blog post](https://example.com/) and [paper](https://example.com/)
20
  πŸš€ Check out the real-time demo in the official [GitHub repository](https://github.com/EleutherAI/aria)
21
  πŸ“Š Get access to our training dataset [Aria-MIDI](https://huggingface.co/datasets/loubb/aria-midi) to train your own models
22
 
@@ -90,6 +90,6 @@ The Aria project has been kindly supported by EleutherAI, Stability AI, as well
90
  author={Bradshaw, Louis and Fan, Honglu and Spangher, Alex and Biderman, Stella and Colton, Simon},
91
  booktitle={arXiv preprint},
92
  year={2025},
93
- url={https://arxiv.org/abs/2504.15071}
94
  }
95
  ```
 
13
 
14
  `Aria` is a pretrained autoregressive generative model for symbolic music based on the LLaMA 3.2 (1B) architecture. It was trained on ~60k hours of MIDI transcriptions of expressive solo-piano recordings. It has been finetuned to produce realistic continuations of solo-piano compositions as well as to produce general-purpose contrastive MIDI embeddings.
15
 
16
+ This HuggingFace page contains weights and usage instructions for the pretrained base model. For the generative model, see [aria-medium-gen](https://huggingface.co/loubb/aria-medium-base/resolve/main/model-gen.safetensors?download=true), and for the embedding model, see [aria-medium-embedding](https://huggingface.co/loubb/aria-medium-embedding).
17
 
18
 
19
+ πŸ“– Read our [paper](https://arxiv.org/abs/2506.23869)
20
  πŸš€ Check out the real-time demo in the official [GitHub repository](https://github.com/EleutherAI/aria)
21
  πŸ“Š Get access to our training dataset [Aria-MIDI](https://huggingface.co/datasets/loubb/aria-midi) to train your own models
22
 
 
90
  author={Bradshaw, Louis and Fan, Honglu and Spangher, Alex and Biderman, Stella and Colton, Simon},
91
  booktitle={arXiv preprint},
92
  year={2025},
93
+ url={https://arxiv.org/abs/2506.23869}
94
  }
95
  ```