Commit message (Expand) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Update copyright | Jon Bratseth | 2023-10-09 | 4 | -6/+6 |
* | HuggingFace Tokenizer expects path to be a directory | Bjørn Christian Seime | 2023-08-31 | 1 | -2/+18 |
* | Prefer truncation configuration from tokenizer model | Bjørn Christian Seime | 2023-06-12 | 2 | -13/+104 |
* | Test padding with truncation | Bjørn Christian Seime | 2023-06-08 | 1 | -1/+1 |
* | Disable padding and make it configurable | Bjørn Christian Seime | 2023-06-08 | 1 | -3/+7 |
* | Introduce services.xml syntax for configuring HuggingFace embedders | Bjørn Christian Seime | 2023-06-02 | 1 | -0/+1 |
* | Make truncation and max length configurable | Bjørn Christian Seime | 2023-05-26 | 1 | -4/+14 |
* | Implement deconstruct | Bjørn Christian Seime | 2023-05-16 | 1 | -0/+1 |
* | Revert "Revert "Bjorncs/huggingface tokenizer"" | Bjørn Christian Seime | 2023-05-12 | 3 | -0/+172 |
* | Revert "Bjorncs/huggingface tokenizer" | Arnstein Ressem | 2023-05-12 | 3 | -172/+0 |
* | Disable special tokens by default | Bjørn Christian Seime | 2023-05-11 | 1 | -12/+7 |
* | Mark HF integration as beta | Bjørn Christian Seime | 2023-05-11 | 2 | -0/+5 |
* | Make HF tokenizer a separate embedder | Bjørn Christian Seime | 2023-05-11 | 3 | -0/+172 |