Generalize parse state cloning #172
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
brandonwillard
force-pushed
the
generalize-parse-state-cloning
branch
from
86b982d
to
9368a8d
Compare
This just makes it easier to cut down on unnecessary copying.
brandonwillard
force-pushed
the
generalize-parse-state-cloning
branch
from
5224979
to
7f3fae3
Compare
rlouf
reviewed
Jul 9, 2023
| @@ -26,23 +27,33 @@ | |||
| checkpoint, trust_remote_code=True, revision=revision | |||
| ).to(device) | |||
|
|
|||
| input_text = "def " | |||
| inputs = tokenizer.encode(input_text, return_tensors="pt").to(device) | |||
| sql_grammar_url = "https://github.com/zbrookle/sql_to_ibis/raw/0e9226da42065940ce21439d490f9fcacadc7f92/sql_to_ibis/grammar/sql.lark" | |||
There was a problem hiding this comment.
What do you think about maintaining some of the grammars we need?
There was a problem hiding this comment.
Yeah, we can add them with the appropriate licenses, of course.
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Outdated suggestions cannot be applied.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.
This PR makes some simple generalizations to our custom
larkparse state cloning. It also adds SQL-guided generation as an extension to the existing LLM example.N.B. Don't expect the example model (i.e.
codegen-350M-mono) to actually produce meaningful/interesting SQL; it was trained primarily/exclusively on Python code. Also, the example SQL grammar could have issues of its own.