microsoft / microsoft/onnxruntime-extensions
NER transformers model packed in one onnx file with Sentencepiece Tokenizer
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 479
- Forks
- 144
- Avg merge
- 1d 8h
- Merged PRs (30d)
- 11
Description
Hi, I'm not getting all the stakes of this package, but is there a way to use the scripts to get a Java tokenizer ?
I converted my python model to onnx and I aiming to run it with a Java runtime, but I don't get a clear comprehension of what the extension is designed for ? Is there a way to use it with Java Sentencepiece tokenizer ?
I read on your docs that a lot of tokenizers are supported but is it only for Python ? (here)
Best regards
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with docs/custom_text_ops.md, specifically the tokenizer section linked in the issue, and determine how the documented tokenizer support relates to a Java runtime and SentencePiece. Done would be a documented, confirmed path for Java use or a clearly scoped support change.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- java, python
- Domain
- tooling
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100