dotnet / dotnet/machinelearning
[Tokenizers] Port CLIP Tokenizer
Open
area-Tokenizers
enhancement
Priority:2
- Dominant language
- C#
- Stars
- 9.4k
- Forks
- 2k
- Avg merge
- 2d 20h
- Merged PRs (30d)
- 11
Description
Port CLIP tokenizer which leverages byte-level BPE. This tokenizer enables scenarios like StableDiffusion
May be dependent on https://github.com/dotnet/machinelearning/issues/6992.
Reference:
https://huggingface.co/docs/transformers/main/en/model_doc/clip
https://github.com/huggingface/transformers/blob/0549000c5bf6c7249f411917f2a6f0b6d0f06da1/src/transformers/models/codegen/tokenization_codegen.py#L98
https://onnxruntime.ai/docs/tutorials/csharp/stable-diffusion-csharp.html#tokenization-with-onnx-runtime-extensions
Paper:
https://arxiv.org/abs/2103.00020
https://arxiv.org/pdf/2103.00020.pdf
Contributor guide
Assessment
This issue has not been assessed yet.