Skip to content
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.

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

add EOS token to modulartokenizer #44

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Conversation

floccinauc
Copy link
Collaborator

No description provided.

@floccinauc floccinauc self-assigned this May 24, 2023
Copy link
Collaborator

@mosheraboh mosheraboh left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Just saw this relatively old PR.
Is it still relevant?
I left comments inline anyway

@@ -98,7 +98,7 @@ def get_training_corpus(dataset: List) -> Generator:
print("Fin")


@hydra.main(config_path="./configs", config_name="tokenizer_config", version_base=None)
@hydra.main(config_path="./configs", config_name="tokenizer_config_personal", version_base=None)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

personal?

@@ -0,0 +1,136 @@
import hydra
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What is this file? test? script that creates modular tokenizer?
Why is titan relevant here?

@@ -0,0 +1,46 @@
paths:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

any chance we can always use smaller case in variable and files names (including AA and SMILES)

data:
tokenizer:
# modular_tokenizers_out_path: "${paths.tokenizers_path}/modular_wordlevelAA_BPESMILES/"
overall_max_len: 70
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why do you need to specify the max_len here? We should specify it per task.

# max_len: 100 # [Optional] max number of tokens to be used by all instances of this tokenizer. If None or undefined, no limit is set.
start_delimiter: "<start_AA>"
end_delimiter: "<end_AA>"
- name: AA
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What is the difference between AA and AA nonspecial?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants