e4d31a40db
fix: bump clients test base url to llama ( #1751 )
...
This PR bumps the client tests from `google/flan-t5-xxl` to
`meta-llama/Llama-2-7b-chat-hf` to resolve issues when calling the
endpoint and `google/flan-t5-xxl` is not available
run with
```bash
make python-client-tests
clients/python/tests/test_client.py .............. [ 43%]
clients/python/tests/test_errors.py .......... [ 75%]
clients/python/tests/test_inference_api.py ...... [ 93%]
clients/python/tests/test_types.py .. [100%]
```
**note `google/flan-t5-xxl` function is currently unused but still
included in the `conftest.py`
2024-04-16 16:56:47 -04:00
1e03b61b5c
Revert "Modify default for max_new_tokens in python client ( #1336 )"
...
This reverts commit 2d56f106a6
2024-02-01 14:36:10 +00:00
2d56f106a6
Modify default for max_new_tokens in python client ( #1336 )
...
# What does this PR do?
Since
([#1097 ](https://github.com/huggingface/text-generation-inference/pull/1097 ))
the clients do not need to specify a max_length anymore. However, the
python client in this repo had not yet been adapted to these changes.
This PR makes it possible to use the python client and not provide
max_new_tokens.
<!-- Remove if not applicable -->
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [x] Did you read the [contributor
guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests ),
Pull Request section?
- [ ] 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 ).
- [x] Did you write any new necessary tests?
## Who can review?
Anyone in the community is free to review the PR once the tests have
passed. Feel free to tag
members/contributors who may be interested in your PR.
2024-01-29 11:02:57 -05:00
895c5f1562
feat(server): only compute prefill logprobs when asked ( #406 )
...
Close #288
2023-06-02 17:12:30 +02:00
dbdc587ddd
feat(integration-tests): improve comparison and health checks ( #336 )
2023-05-16 20:22:11 +02:00
f092ba9b22
feat(server): add watermarking tests ( #248 )
2023-04-27 19:16:35 +02:00
b927244eb5
feat(python-client): get list of currently deployed tgi models using the inference API ( #191 )
2023-04-17 18:43:24 +02:00
53ee09c0b0
fea(dockerfile): better layer caching ( #159 )
2023-04-14 10:12:21 +02:00
d6a93fe992
fix(server): fix flash-neox scores warping ( #137 )
2023-03-24 18:21:41 +01:00
d8dc8f1b0c
feat(python-client): add new parameters ( #118 )
2023-03-09 16:05:33 +01:00
3fef90d50f
feat(clients): Python client ( #103 )
2023-03-07 18:52:22 +01:00
drbh