This repository has been archived by the owner on Dec 25, 2023. It is now read-only.
Laboratory work #4, Marina Mokina - 22FPL1 #175
Closed
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
delete requirements
artyomtugaryov
suggested changes
Dec 7, 2023
lab_4_fill_words_by_ngrams/main.py
Outdated
| @@ -98,6 +134,35 @@ def run(self, seq_len: int, prompt: str) -> str: # type: ignore | |||
| or if sequence has inappropriate length, | |||
| or if methods used return None. | |||
| """ | |||
| if not (isinstance(seq_len, int) and seq_len > 0 | |||
| and isinstance(prompt, str) and prompt): | |||
| raise ValueError | |||
There was a problem hiding this comment.
please, add some message to error
lab_4_fill_words_by_ngrams/main.py
Outdated
| if not next_tokens: | ||
| break | ||
|
|
||
| sorted_dict = dict(sorted(list(next_tokens.items()), key=lambda x: (x[1], x[0]), reverse=True)) |
There was a problem hiding this comment.
do you actually need list to do sorting?
artyomtugaryov
suggested changes
Dec 14, 2023
lab_4_fill_words_by_ngrams/main.py
Outdated
| @@ -28,6 +32,19 @@ def _tokenize(self, text: str) -> tuple[str, ...]: # type: ignore | |||
| Raises: | |||
| ValueError: In case of inappropriate type input argument or if input argument is empty. | |||
| """ | |||
| if not isinstance(text, str) or not text: | |||
| raise ValueError('WordProcessor._tokenize: Incorrect input') | |||
There was a problem hiding this comment.
remove WordProcessor._tokenize from the message
lab_4_fill_words_by_ngrams/main.py
Outdated
|
|
||
| tokens = [] | ||
| for word in text.lower().split(): | ||
| if word[-1] in '!?.': |
There was a problem hiding this comment.
'!?.' to a variable
lab_4_fill_words_by_ngrams/main.py
Outdated
| @@ -125,6 +195,8 @@ def get_conversion_generator_type(self, generator_type: int) -> str: # type: ig | |||
| Returns: | |||
| (str): Name of the generator. | |||
| """ | |||
| generators = ['Greedy Generator', 'Top-P Generator', 'Beam Search Generator'] | |||
There was a problem hiding this comment.
what if generator_type is 4?
artyomtugaryov
suggested changes
Dec 17, 2023
lab_4_fill_words_by_ngrams/main.py
Outdated
| for i in range(seq_len): | ||
| next_tokens = self._model.generate_next_token(encoded) | ||
| if next_tokens is None: | ||
| raise ValueError |
lab_4_fill_words_by_ngrams/main.py
Outdated
|
|
||
| decoded = self._word_processor.decode(encoded) | ||
| if not decoded: | ||
| raise ValueError |
lab_4_fill_words_by_ngrams/main.py
Outdated
| @@ -125,6 +196,12 @@ def get_conversion_generator_type(self, generator_type: int) -> str: # type: ig | |||
| Returns: | |||
| (str): Name of the generator. | |||
| """ | |||
| types = { | |||
|
Well done! Good job! |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.