Update README.md
Browse files
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 |
-
π Read our [
|
20 |
π Check out the real-time demo in the official [GitHub repository](https://github.com/EleutherAI/aria)
|
21 |
π 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/
|
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 |
+
π Read our [paper](https://arxiv.org/abs/2506.23869)
|
20 |
π Check out the real-time demo in the official [GitHub repository](https://github.com/EleutherAI/aria)
|
21 |
π 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 |
```
|