Allow tokenizer to customize stop_tokens #84
Merged
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
qihqi
force-pushed
the
hanq_dev
branch
3 times, most recently
from
442972c to
af8ae17
Compare
FanhaiLu1
reviewed
May 17, 2024
jetstream/engine/token_utils.py
Outdated
| @@ -349,6 +349,11 @@ def bos_id(self) -> int: | |||
| """ID of the BOS token.""" | |||
| return self.vocab.bos_id | |||
|
|
|||
| @property | |||
There was a problem hiding this comment.
Unless we want to return different stop_tokens, we don't need this function in child class.
Remove the stop_tokens function here does not affect behavior. By default, it will call parent stop_tokens.
| @@ -395,6 +400,11 @@ def decode(self, token_ids: list[int]) -> str: | |||
| """ | |||
| return self.tokenizer.decode(token_ids) | |||
|
|
|||
| @property | |||
There was a problem hiding this comment.
same, remove this function in child class will not affect behavior.
There was a problem hiding this comment.
jetstream/engine/token_utils.py
Outdated
| def stop_tokens(self) -> set[int]: | ||
| """ID of the stop token.""" | ||
| return {self.eos_id, self.pad_id} | ||
|
|
||
|
|
There was a problem hiding this comment.
@JoeZijunZhou What is TikToken? (some tokenizer from tiktok or? )
There was a problem hiding this comment.
it's llama3's tokenizer (apperently made by OpenAI)
bhavya01
approved these changes
May 17, 2024
FanhaiLu1
approved these changes
May 17, 2024
This was referenced May 17, 2024
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Outdated suggestions cannot be applied.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.
No description provided.