diff options
| author | Victor-Mihaila <115141117+Victor-Mihaila@users.noreply.github.com> | 2024-04-13 11:07:28 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-04-13 11:07:28 +0200 |
| commit | fb805b8ca2c9413ad9227800328145434a08eaca (patch) | |
| tree | 56b64200bf04fc6dd0dbe1bf021ff81eff0bb828 /candle-nn | |
| parent | 79e3bec789bd7bdb0e331d628c8fe9d06c519f33 (diff) | |
| download | candle-fb805b8ca2c9413ad9227800328145434a08eaca.tar.gz candle-fb805b8ca2c9413ad9227800328145434a08eaca.tar.bz2 candle-fb805b8ca2c9413ad9227800328145434a08eaca.zip | |
Avoid crashes when running T5 models with F16 tensors on CPU (#2047)
* This change avoids crashes when running T5 models with F16 tensors on CPU.
* This enables running ProstT5's (https://huggingface.co/Rostlab/ProstT5) encoder-only mode in Candle. This ProstT5 mode stores it's embed_tokens weights within the encoder, as its decoding stage was replaced with a CNN. You could write more, like: This alone is not sufficient to run ProstT5 within Candle examples. We will develop a ProstT5 runner outside candle for now, but would be willing to upstream it to candle-examples at a later point.
* Revert "This enables running ProstT5's (https://huggingface.co/Rostlab/ProstT5) encoder-only mode in Candle. This ProstT5 mode stores it's embed_tokens weights within the encoder, as its decoding stage was replaced with a CNN. You could write more, like: This alone is not sufficient to run ProstT5 within Candle examples. We will develop a ProstT5 runner outside candle for now, but would be willing to upstream it to candle-examples at a later point."
This reverts commit d886d3ce5e3f1504934f4f6f7cf86108b7efd191.
Diffstat (limited to 'candle-nn')
0 files changed, 0 insertions, 0 deletions