medcat.utils.relation_extraction.llama.tokenizer

Module Contents

Classes

TokenizerWrapperLlama_RelationExtraction

Wrapper around a huggingface Llama tokenizer so that it works with the

Attributes

logger

medcat.utils.relation_extraction.llama.tokenizer.logger
class medcat.utils.relation_extraction.llama.tokenizer.TokenizerWrapperLlama_RelationExtraction(hf_tokenizers=None, max_seq_length=None, add_special_tokens=False)

Bases: medcat.utils.relation_extraction.tokenizer.BaseTokenizerWrapper_RelationExtraction

Wrapper around a huggingface Llama tokenizer so that it works with the RelCAT models.

Parameters:
  • hf_tokenizers (transformers.LlamaTokenizerFast) – A huggingface Fast Llama.

  • max_seq_length (Optional[int]) –

  • add_special_tokens (Optional[bool]) –

name = 'tokenizer_wrapper_llama_rel'
pretrained_model_name_or_path = 'meta-llama/Llama-3.1-8B'
classmethod load(tokenizer_path, relcat_config, **kwargs)
Parameters:
Return type:

TokenizerWrapperLlama_RelationExtraction