Stéphan Tulkens

The Hugging Face tokenizer.json spec allows you to hide a prompt in a post processor.

Under a very specific but nevertheless very common reading of the practice of “tokenization”, tokenizers are things that turn a string into sequences of atomic identifiers, i.e., integers.

skeletoken has a new version!

The English Writer and Christian apologist G.

I recently listened to the album Music for Existing by producer Martyn.

If you’ve ever used code from scikit-learn, you will have seen the following pattern: import numpy as np from sklearn.preprocessing import StandardScaler X = np.random.randn((100, 32)) scaler = StandardScaler() scaler.fit(X) X_transformed = scaler.tran…

The group of researchers associated with the Massive Text Embedding Benchmark (MTEB) has released a new benchmark: the Retrieval Text Embedding Benchmark.

Without reducing dimensionality, static models can be hundreds of MB large.

Late interaction is an interesting paradigm for computing the similarity between two documents, and can be seen as a hybrid of sparse and dense retrieval.

In a previous post, I showed that making a tokenizer greedy, that is, always picking the longest matching subword like WordPiece does, can improve results without retraining.