onnx-tensorflow
tokenizers
Our great sponsors
onnx-tensorflow | tokenizers | |
---|---|---|
6 | 8 | |
1,237 | 8,424 | |
1.2% | 3.1% | |
0.0 | 8.5 | |
about 1 month ago | 1 day ago | |
Python | Rust | |
GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
onnx-tensorflow
-
How to Solve "BackendIsNotSupposedToImplementIt: Unsqueeze version 13 is not implemented."?
How to solve this? I found below github issue which they solved i think, but im not to able to find the solution https://github.com/onnx/onnx-tensorflow/pull/1022
-
[D] Library to transfer PyTorch to TF
Okay, maybe it worked some years ago. The issue currently is that the trainable weights get lost...which is by design https://github.com/onnx/onnx-tensorflow/issues/1002
-
Has anyone successfully converted an onnx model to tensorflow? Here's the problems I'm having...
TLDR: I'm using onnx-tf to convert an onnx model to tensorflow. During the conversion I lose important information such as inputs, outputs and the names of operators. Please read on if you have experience with this library or you've experienced similar issues. :)
-
Portability of Rust in 2021
We had a few small issues with ONNX. Export worked but when running with e.g. tflite stumbled for example across this https://github.com/onnx/onnx-tensorflow/issues/853 Also the support for sampling from distributions is generally still pretty weak, but we were able to work around that.
-
[D] How to reduce latency of DL models
https://pytorch.org/tutorials/advanced/super\_resolution\_with\_onnxruntime.html https://github.com/onnx/onnx-tensorflow
-
Possible to retrain onnx model?
https://github.com/onnx/onnx-tensorflow Haven’t tried it, let me know if it works.
tokenizers
-
HF Transfer: Speed up file transfers
Hugging Face seems to like Rust. They also wrote Tokenizers in Rust.
-
LLM custom dictionary
Your intuition is right. There are two ways (in increasing order of result performance) : 1. You can simply extend vocab file of the tokenizer and test the predictions 2. You can extend the vocab file and re-train your model on custom data which has these new tokens. Check the following issue on GitHub : https://github.com/huggingface/tokenizers/issues/247
-
[D] SentencePiece, WordPiece, BPE... Which tokenizer is the best one?
SentencePiece -> implementation of some algorithms (there are several others, https://github.com/microsoft/BlingFire https://github.com/glample/fastBPE https://github.com/huggingface/tokenizers )
-
Portability of Rust in 2021
In sum I would like the idea to go with Rust as I more or less got to rewrite the whole thing anyway, but I am a bit skeptical if I will be able to interface with everything that might come up at some point. Or probably end up in a wrapper hell if I got to use more C++ libraries. On the other hand there are definitely a few Rust projects out there that might come in handy (for example https://github.com/huggingface/tokenizers). And the build process is pretty awful right now (CMake it is but with lots of hacks).
-
[D] What's going to be the dominant language for machine learning in 5 years?
A full machine learning pipeline usually comprises far more than just the model, and this is the area where Rust may shine (the recent work by HuggingFace and their https://github.com/huggingface/tokenizers library is a good example)
-
substitute for tokenizer in torchtext
As for other tokenizers, you can take a look at - Huggingface tokenizers library: https://github.com/huggingface/tokenizers - NLTK tokenize: https://www.nltk.org/api/nltk.tokenize.html - Polygot: https://pypi.org/project/polyglot/
-
PyO3: Rust Bindings for the Python Interpreter
Huggingface Tokenizers (https://github.com/huggingface/tokenizers), which are now used by default in their Transformers Python library, use pyO3 and became popular due to the pitch that it encoded text an order of magnitude faster with zero config changes.
It lives up to that claim. (I had issues with return object typing when going between Python/Rust at first but those are more consistent now)
-
Rusticles #19 - Wed Nov 11 2020
huggingface/tokenizers (Rust): 💥Fast State-of-the-Art Tokenizers optimized for Research and Production
What are some alternatives?
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
netron - Visualizer for neural network, deep learning and machine learning models
setuptools-rust - Setuptools plugin for Rust support
guesslang - Detect the programming language of a source code
BlingFire - A lightning fast Finite State machine and REgular expression manipulation library.
models - Models and examples built with TensorFlow
rayon - Rayon: A data parallelism library for Rust
pytorch2keras - PyTorch to Keras model convertor
tch-rs - Rust bindings for the C++ api of PyTorch.
yolo-tf2 - yolo(all versions) implementation in keras and tensorflow 2.x
rust-bert - Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)