Sai5480/monolingual-tokenizer-native-mal-vocab-128000

Monolingual Tokenizer - Malayalam (Vocab 128000)

This is a monolingual tokenizer trained on Malayalam text with vocabulary size 128000.

Usage

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("monolingual-tokenizer-native-mal-vocab-128000")

Files

• mal.model: SentencePiece model file
• mal.vocab: Vocabulary file
• config.json: Tokenizer configuration

Training Details

• Language: Malayalam (mal)
• Vocabulary Size: 128000
• Model Type: SentencePiece Unigram