v.0.2.0: More providers, extractors, examples, and refactor🥳
The 0.2.0 release of TextMachina includes:
- New providers:
Amazon Bedrock
,AI21
,Azure OpenAI
, and inference servers (vllm
andtrt
). - Refactor the Huggingface Remote provider to make retries through
HTTPAdapter
. - Two new extractors for mixcase tasks:
sentence_masking
andword_masking
. Differently from thesentence_gap
andword_gap
extractors, LLMs must reconstruct masks in whole texts, instead of writing text between boundaries. - Extend the dataset generator for mixcase tasks to consider masking extractors.
- Add config examples to learn about the extractors.
- Small refactors: colors in logger, inheritance in some tokenizers, etc.