text-generation-inference/server/text_generation_server
Dean Wyatte 27daa511ec GPTNeoX: Use static rotary embedding (#1498)
# What does this PR do?

`transformers` 4.35 removed rotary embeddings from GPTNeoX's weights
([link to line
diff](253f9a3f97 (diff-0e2a05d86c82e96f516db8c14070ceb36f53ca44c6bc21a9cd92ad2e777b9cf1R298))).
This applies the same fix as
https://github.com/huggingface/text-generation-inference/pull/793 which
generates them on-the-fly using the appropriate value from the config
file

Fixes
https://github.com/huggingface/text-generation-inference/issues/1460

## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Did you read the [contributor
guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
      Pull Request section?
- [x] Was this discussed/approved via a Github issue or the
[forum](https://discuss.huggingface.co/)? Please add a link
      to it if that's the case.
- [ ] Did you make sure to update the documentation with your changes?
Here are the
[documentation
guidelines](https://github.com/huggingface/transformers/tree/main/docs),
and
[here are tips on formatting
docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
- [ ] Did you write any new necessary tests?


## Who can review?

@OlivierDehaene OR @Narsil
2024-04-23 09:21:21 +03:00
..
models GPTNeoX: Use static rotary embedding (#1498) 2024-04-23 09:21:21 +03:00
pb feat(server): clear cache on error (#143) 2023-03-28 11:29:35 +02:00
utils Fixing top_n_tokens. (#1497) 2024-04-23 08:49:24 +03:00
__init__.py feat(clients): Python client (#103) 2023-03-07 18:52:22 +01:00
cache.py fix(server): decrease memory fragmentation (#557) 2023-07-06 14:28:33 +02:00
cli.py v1.4.0 (#1494) 2024-04-22 15:47:42 +03:00
habana_quantization_env.py Add Habana copyright header (#122) 2024-04-08 18:06:21 +02:00
interceptor.py Add Habana copyright header (#122) 2024-04-08 18:06:21 +02:00
server.py fix: fix gpt-q with groupsize = -1 (#1358) 2024-04-19 15:05:50 +03:00
tgi_service.py Speculative (#1308) 2024-04-18 12:39:39 +00:00
tracing.py feat(clients): Python client (#103) 2023-03-07 18:52:22 +01:00