README.md

metadata

library_name: transformers
license: apache-2.0
tags:
  - tokenizer
  - claude3
  - t5

claude3 tokenizer: for T5

Vocabulary size: 65103

• relevant special tokens for T5 training added
• post processor updated following t5's tokenizer

usage:

from transformers import AutoTokenizer
tk = AutoTokenizer.from_pretrained('BEE-spoke-data/claude-tokenizer-forT5')
inputs = tk("here are some words", return_tensors="pt")

post processor

"post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "</s>",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "</s>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "</s>",
          "type_id": 0
        }
      }
    ],
    "special_tokens": {
      "</s>": {
        "id": "</s>",
        "ids": [
          65001
        ],
        "tokens": [
          "</s>"
        ]
      }
    }
  },