Nougat modified to huggingface interface #178
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
CluckRookie
requested review from
CambioML,
goldmermaid,
SayaZhang and
SeisSerenata
as code owners
CambioML
approved these changes
Feb 16, 2024
| except ModuleNotFoundError as exc: | ||
| raise ModuleNotFoundError( | ||
| "Please install nougat to use NougatModelServer. You can use `pip install nougat-ocr` to install it." | ||
| "Please install nougat to use NougatModelServer. You can use `pip install transformers` to install it." |
There was a problem hiding this comment.
nit: might also require to install torch.
uniflow/op/model/model_server.py
Outdated
Comment on lines
585
to
587
| from PIL import Image | ||
| import pypdfium2 |
There was a problem hiding this comment.
nit: can consider to move this to init.
| model_name: str = "0.1.0-small" | ||
| batch_size: int = 1 | ||
| model_name: str = "facebook/nougat-small" | ||
| batch_size: int = 2 |
uniflow/op/model/model_server.py
Outdated
| if is_last_page[j]: | ||
| out = "".join(predictions).strip() | ||
| out = re.sub(r"\n{3,}", "\n\n", out).strip() | ||
| sequence = self.processor.batch_decode(outputs, skip_special_tokens=True)#[0] |
CambioML
reviewed
Feb 16, 2024
Comment on lines
+609
to
+616
| pad_token_id=self.processor.tokenizer.pad_token_id, | ||
| eos_token_id=self.processor.tokenizer.eos_token_id, |
There was a problem hiding this comment.
nit: does nougatprocess has a tokenizer?
update by running black and isort reformat.
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Outdated suggestions cannot be applied.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.