Generation: fix test #34369
Merged
Generation: fix test #34369
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
gante
approved these changes
Oct 25, 2024
| # code is up to date with our most recent standards | ||
| if ( | ||
| "inputs_embeds" in prepare_inputs_for_generation_args | ||
| and "cache_positions" in prepare_inputs_for_generation_args |
There was a problem hiding this comment.
so this part was never executed, because of the typo in cache_positions -- correct?
| outputs_from_ids = model.generate( | ||
| input_ids, max_new_tokens=5, return_dict_in_generate=True, output_scores=True | ||
| ) | ||
| outputs_from_ids = model.generate(input_ids, max_new_tokens=5, **generation_kwargs) |
There was a problem hiding this comment.
nit: max_new_tokens can be moved to generation_kwargs
BernardZach
pushed a commit
to BernardZach/transformers
that referenced
this pull request
Dec 5, 2024
* fix test * fix copies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Fixes one part of the test that was not being triggered when we run it with
pytestbecause it had typo incache_position(S). Fixing the typo resulted in a whole bunch of errors most of which are caused by apparently non-deterministic output when setting therepetition_penalty. Thus I moved the test for beam-search + input-embeds to another placeThe main idea when writing this test was to make sure beam search works with inputs embeds for decoder-only models that now support new cache format, so I think the change should be fine