Skip to content

Generate: add missing logits processors docs #25653

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Aug 25, 2023
Merged

Generate: add missing logits processors docs #25653

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
3f9723d
Add missing logits processors docs
gante Aug 22, 2023
5b371ed
add missing imports
gante Aug 22, 2023
14d9750
more missing imports
gante Aug 22, 2023
6e04a9d
more missing imports
gante Aug 22, 2023
807fa5d
tmp commit
gante Aug 23, 2023
697f8b8
sort docs by alphabetical order; Add missing output classes; Separate…
gante Aug 23, 2023
e7c75a0
typo
gante Aug 23, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
174 changes: 132 additions & 42 deletions docs/source/en/internal/generation_utils.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,39 +75,104 @@ values. Here, for instance, it has two keys that are `sequences` and `scores`.
We document here all output types.


### GreedySearchOutput

[[autodoc]] generation.GreedySearchDecoderOnlyOutput
### PyTorch

[[autodoc]] generation.GreedySearchEncoderDecoderOutput

[[autodoc]] generation.FlaxGreedySearchOutput
[[autodoc]] generation.GreedySearchDecoderOnlyOutput

### SampleOutput
[[autodoc]] generation.SampleEncoderDecoderOutput

[[autodoc]] generation.SampleDecoderOnlyOutput

[[autodoc]] generation.SampleEncoderDecoderOutput
[[autodoc]] generation.BeamSearchEncoderDecoderOutput

[[autodoc]] generation.FlaxSampleOutput
[[autodoc]] generation.BeamSearchDecoderOnlyOutput

### BeamSearchOutput
[[autodoc]] generation.BeamSampleEncoderDecoderOutput

[[autodoc]] generation.BeamSearchDecoderOnlyOutput
[[autodoc]] generation.BeamSampleDecoderOnlyOutput

[[autodoc]] generation.BeamSearchEncoderDecoderOutput
[[autodoc]] generation.ContrastiveSearchEncoderDecoderOutput

### BeamSampleOutput
[[autodoc]] generation.ContrastiveSearchDecoderOnlyOutput

[[autodoc]] generation.BeamSampleDecoderOnlyOutput
### TensorFlow

[[autodoc]] generation.BeamSampleEncoderDecoderOutput
[[autodoc]] generation.TFGreedySearchEncoderDecoderOutput

[[autodoc]] generation.TFGreedySearchDecoderOnlyOutput

[[autodoc]] generation.TFSampleEncoderDecoderOutput

[[autodoc]] generation.TFSampleDecoderOnlyOutput

[[autodoc]] generation.TFBeamSearchEncoderDecoderOutput

[[autodoc]] generation.TFBeamSearchDecoderOnlyOutput

[[autodoc]] generation.TFBeamSampleEncoderDecoderOutput

[[autodoc]] generation.TFBeamSampleDecoderOnlyOutput

[[autodoc]] generation.TFContrastiveSearchEncoderDecoderOutput

[[autodoc]] generation.TFContrastiveSearchDecoderOnlyOutput

### FLAX

[[autodoc]] generation.FlaxSampleOutput

[[autodoc]] generation.FlaxGreedySearchOutput

[[autodoc]] generation.FlaxBeamSearchOutput

## LogitsProcessor

A [`LogitsProcessor`] can be used to modify the prediction scores of a language model head for
generation.

### PyTorch

[[autodoc]] AlternatingCodebooksLogitsProcessor
- __call__

[[autodoc]] ClassifierFreeGuidanceLogitsProcessor
- __call__

[[autodoc]] EncoderNoRepeatNGramLogitsProcessor
- __call__

[[autodoc]] EncoderRepetitionPenaltyLogitsProcessor
- __call__

[[autodoc]] EpsilonLogitsWarper
- __call__

[[autodoc]] EtaLogitsWarper
- __call__

[[autodoc]] ExponentialDecayLengthPenalty
- __call__

[[autodoc]] ForcedBOSTokenLogitsProcessor
- __call__

[[autodoc]] ForcedEOSTokenLogitsProcessor
- __call__

[[autodoc]] ForceTokensLogitsProcessor
- __call__

[[autodoc]] HammingDiversityLogitsProcessor
- __call__

[[autodoc]] InfNanRemoveLogitsProcessor
- __call__

[[autodoc]] LogitNormalization
- __call__

[[autodoc]] LogitsProcessor
- __call__

Expand All @@ -123,61 +188,63 @@ generation.
[[autodoc]] MinNewTokensLengthLogitsProcessor
- __call__

[[autodoc]] TemperatureLogitsWarper
[[autodoc]] NoBadWordsLogitsProcessor
- __call__

[[autodoc]] RepetitionPenaltyLogitsProcessor
[[autodoc]] NoRepeatNGramLogitsProcessor
- __call__

[[autodoc]] TopPLogitsWarper
[[autodoc]] PrefixConstrainedLogitsProcessor
- __call__

[[autodoc]] TopKLogitsWarper
[[autodoc]] RepetitionPenaltyLogitsProcessor
- __call__

[[autodoc]] TypicalLogitsWarper
[[autodoc]] SequenceBiasLogitsProcessor
- __call__

[[autodoc]] NoRepeatNGramLogitsProcessor
[[autodoc]] SuppressTokensAtBeginLogitsProcessor
- __call__

[[autodoc]] SequenceBiasLogitsProcessor
[[autodoc]] SuppressTokensLogitsProcessor
- __call__

[[autodoc]] NoBadWordsLogitsProcessor
[[autodoc]] TemperatureLogitsWarper
- __call__

[[autodoc]] PrefixConstrainedLogitsProcessor
[[autodoc]] TopKLogitsWarper
- __call__

[[autodoc]] HammingDiversityLogitsProcessor
[[autodoc]] TopPLogitsWarper
- __call__

[[autodoc]] ForcedBOSTokenLogitsProcessor
[[autodoc]] TypicalLogitsWarper
- __call__

[[autodoc]] ForcedEOSTokenLogitsProcessor
[[autodoc]] UnbatchedClassifierFreeGuidanceLogitsProcessor
- __call__

[[autodoc]] InfNanRemoveLogitsProcessor
[[autodoc]] WhisperTimeStampLogitsProcessor
- __call__

[[autodoc]] TFLogitsProcessor
### TensorFlow

[[autodoc]] TFForcedBOSTokenLogitsProcessor
- __call__

[[autodoc]] TFLogitsProcessorList
[[autodoc]] TFForcedEOSTokenLogitsProcessor
- __call__

[[autodoc]] TFLogitsWarper
[[autodoc]] TFForceTokensLogitsProcessor
- __call__

[[autodoc]] TFTemperatureLogitsWarper
[[autodoc]] TFLogitsProcessor
- __call__

[[autodoc]] TFTopPLogitsWarper
[[autodoc]] TFLogitsProcessorList
- __call__

[[autodoc]] TFTopKLogitsWarper
[[autodoc]] TFLogitsWarper
- __call__

[[autodoc]] TFMinLengthLogitsProcessor
Expand All @@ -192,10 +259,30 @@ generation.
[[autodoc]] TFRepetitionPenaltyLogitsProcessor
- __call__

[[autodoc]] TFForcedBOSTokenLogitsProcessor
[[autodoc]] TFSuppressTokensAtBeginLogitsProcessor
- __call__

[[autodoc]] TFForcedEOSTokenLogitsProcessor
[[autodoc]] TFSuppressTokensLogitsProcessor
- __call__

[[autodoc]] TFTemperatureLogitsWarper
- __call__

[[autodoc]] TFTopKLogitsWarper
- __call__

[[autodoc]] TFTopPLogitsWarper
- __call__

### FLAX

[[autodoc]] FlaxForcedBOSTokenLogitsProcessor
- __call__

[[autodoc]] FlaxForcedEOSTokenLogitsProcessor
- __call__

[[autodoc]] FlaxForceTokensLogitsProcessor
- __call__

[[autodoc]] FlaxLogitsProcessor
Expand All @@ -207,27 +294,30 @@ generation.
[[autodoc]] FlaxLogitsWarper
- __call__

[[autodoc]] FlaxTemperatureLogitsWarper
[[autodoc]] FlaxMinLengthLogitsProcessor
- __call__

[[autodoc]] FlaxTopPLogitsWarper
[[autodoc]] FlaxSuppressTokensAtBeginLogitsProcessor
- __call__

[[autodoc]] FlaxTopKLogitsWarper
[[autodoc]] FlaxSuppressTokensLogitsProcessor
- __call__

[[autodoc]] FlaxForcedBOSTokenLogitsProcessor
[[autodoc]] FlaxTemperatureLogitsWarper
- __call__

[[autodoc]] FlaxForcedEOSTokenLogitsProcessor
[[autodoc]] FlaxTopKLogitsWarper
- __call__

[[autodoc]] FlaxMinLengthLogitsProcessor
[[autodoc]] FlaxTopPLogitsWarper
- __call__

[[autodoc]] FlaxWhisperTimeStampLogitsProcessor
- __call__

## StoppingCriteria

A [`StoppingCriteria`] can be used to change when to stop generation (other than EOS token).
A [`StoppingCriteria`] can be used to change when to stop generation (other than EOS token). Please note that this is exclusivelly available to our PyTorch implementations.

[[autodoc]] StoppingCriteria
- __call__
Expand All @@ -243,7 +333,7 @@ A [`StoppingCriteria`] can be used to change when to stop generation (other than

## Constraints

A [`Constraint`] can be used to force the generation to include specific tokens or sequences in the output.
A [`Constraint`] can be used to force the generation to include specific tokens or sequences in the output. Please note that this is exclusivelly available to our PyTorch implementations.

[[autodoc]] Constraint

Expand Down
Loading