docs: highlight difference between num_parameters() and get_nb_trainable_parameters() in PEFT #1531
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
4 tasks
BenjaminBossan
requested changes
Mar 5, 2024
src/peft/peft_model.py
Outdated
| @@ -515,7 +515,12 @@ def get_nb_trainable_parameters(self) -> tuple[int, int]: | |||
|
|
|||
| def print_trainable_parameters(self) -> None: | |||
| """ | |||
| Prints the number of trainable parameters in the model. | |||
| Prints the number of trainable parameters in the model. Note: print_trainable_parameters() uses | |||
There was a problem hiding this comment.
Could you please add 1 empty line after the first sentence (before "Note")?
src/peft/peft_model.py
Outdated
| @@ -515,7 +515,12 @@ def get_nb_trainable_parameters(self) -> tuple[int, int]: | |||
|
|
|||
| def print_trainable_parameters(self) -> None: | |||
| """ | |||
| Prints the number of trainable parameters in the model. | |||
| Prints the number of trainable parameters in the model. Note: print_trainable_parameters() uses | |||
| get_nb_trainable_parameters() which is different from num_parameters(only_trainable=True). | |||
There was a problem hiding this comment.
Let's mention that num_parameters is a method from transformers.
src/peft/peft_model.py
Outdated
| Prints the number of trainable parameters in the model. | ||
| Prints the number of trainable parameters in the model. Note: print_trainable_parameters() uses | ||
| get_nb_trainable_parameters() which is different from num_parameters(only_trainable=True). | ||
| get_nb_trainable_parameters() returns (trainable parameters, all paramters) of the Peft Model which includes |
src/peft/peft_model.py
Outdated
| get_nb_trainable_parameters() returns (trainable parameters, all paramters) of the Peft Model which includes | ||
| modified backbone transformer model. For techniques like LoRA, the backbone transformer model is modified in | ||
| place with LoRA modules. However, for prompt tuning, the backbone transformer model is unmodified. | ||
| num_parameters(only_trainable=True) returns number of trainable parameters of the backbone transformer model. |
There was a problem hiding this comment.
Just to make it totally clear, let's add here that this can result in a different number :)
…ble_parameters() in PEFT Signed-off-by: Mehant Kammakomati <[email protected]>
kmehant
force-pushed
the
docs-trainable-params
branch
from
a883d87
to
1151fdc
Compare
|
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. |
BenjaminBossan
approved these changes
Mar 5, 2024
BenjaminBossan
pushed a commit
to BenjaminBossan/peft
that referenced
this pull request
Mar 14, 2024
Signed-off-by: Mehant Kammakomati <[email protected]>
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.
related to #1526