support kenlm models and surprisal from them #14
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
…nized text, e.g. whitespace for `kenlm`
…ete CustomEncoding implementation.
… want that? maybe add an option to show but default to disabling it? do we also want bos?
aalok-sathe
commented
Nov 8, 2023
| @@ -17,6 +17,7 @@ plotext = "^5.0.2" | |||
| matplotlib = "^3.5.2" | |||
| pandas = "^1.4.3" | |||
| openai = "^0.23.0" | |||
| kenlm = {version = "^0.2.0", optional = true} | |||
There was a problem hiding this comment.
we don't want to force kenlm as a dependency---only install it if people need it
aalok-sathe
commented
Nov 8, 2023
| accum += [m.BaseScore(st1, w, st2)] | ||
| st1, st2 = st2, st1 | ||
| if eos: | ||
| accum += [m.BaseScore(st1, "</s>", st2)] |
There was a problem hiding this comment.
this part should maybe be made false by default, since this is generating a score for EOS, which is a convention inconsistent with huggingface models surprisal
aalok-sathe
commented
Nov 8, 2023
| from transformers import tokenization_utils_base | ||
|
|
||
|
|
||
| def pick_matching_token_ixs( | ||
| def hf_pick_matching_token_ixs( |
There was a problem hiding this comment.
such a method is not necessary for ngrams, I believe, but need to check how punctuation gets tokenized:
In [10]: [ce] = k.tokenize('hello, my name')
In [11]: ce.tokens
Out[11]: ('hello', ',', 'my', 'name')
|
merging this as it doesn't introduce any changes to anything current; only adds new implementation to support the kenlm model class. merging even though we have a few TODOs to address. |
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Outdated suggestions cannot be applied.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.
in this PR we add support for KenLM models using the KenLM python bindings. note that due to the complications of installing KenLM we don't enforce it as a requirement for the repo, but it should be installed if someone wants to use this library to do inference with KenLM Ngram models using the
kenlmpython interface