zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-12-16 02:08:55 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

MusicGen (#1020)

Browse Source 
* Add MusicGen model

* add benchmarks

* change to from_pretrained

* symlinks

* add readme and requirements

* fix readme

* readme
This commit is contained in:
Alex Barron
2024-10-11 10:16:20 -07:00
committed by GitHub
parent 4360e7ccec
commit d72fdeb4ee
19 changed files with 722 additions and 245 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
t5/README.md
View File

@@ -7,31 +7,6 @@ tasks by prepending task-specific prefixes to the input, e.g.:
This example also supports the FLAN-T5 models variants.[^2]
## Setup
Download and convert the model:
```sh
python convert.py --model <model>
```
This will make the `<model>.npz` file which MLX can read.
The `<model>` can be any of the following:
| Model Name | Model Size |
| ---------- | ----------
| t5-small | 60 million |
| t5-base | 220 million |
| t5-large | 770 million |
| t5-3b | 3 billion |
| t5-11b | 11 billion |
The FLAN variants can be specified with `google/flan-t5-small`,
`google/flan-t5-base`, etc. See the [Hugging Face
page](https://huggingface.co/docs/transformers/model_doc/flan-t5) for a
complete list of models.
## Generate
Generate text with:
@@ -48,6 +23,21 @@ To see a list of options run:
python t5.py --help
```
The `<model>` can be any of the following:
| Model Name | Model Size |
| ---------- | ----------
| t5-small | 60 million |
| t5-base | 220 million |
| t5-large | 770 million |
| t5-3b | 3 billion |
| t5-11b | 11 billion |
The FLAN variants can be specified with `google/flan-t5-small`,
`google/flan-t5-base`, etc. See the [Hugging Face
page](https://huggingface.co/docs/transformers/model_doc/flan-t5) for a
complete list of models.
[^1]: For more information on T5 see the [original paper](https://arxiv.org/abs/1910.10683)
or the [Hugging Face page](https://huggingface.co/docs/transformers/model_doc/t5).
[^2]: For more information on FLAN-T5 see the [original paper](https://arxiv.org/abs/2210.11416).