Upload tokenizer.py

tokenizer.py

@@ -0,0 +1,56 @@
+input_file = "/content/bothcan.txt" # Replace with actual input file path
+model_prefix = "botchan" # Replace with desired model save path
+import sentencepiece as spm
+spm.SentencePieceTrainer.train(
+input=input_file,
+model_prefix=model_prefix,
+vocab_size=1000, # Adjust as needed, this is just an example value
+model_type="unigram", # You can use different models like unigram or bpe
+)
+
+from sentencepiece import SentencePieceProcessor
+
+model_path = "botchan.model" # Replace with the actual path
+sp_model = SentencePieceProcessor(model_file=model_path)
+vocab_size = 4000
+
+import os
+from logging import getLogger
+from typing import List
+
+from sentencepiece import SentencePieceProcessor
+
+
+logger = getLogger()
+
+
+class Tokenizer:
+    def __init__(self, model_path: str):
+        # reload tokenizer
+        assert os.path.isfile(model_path), model_path
+        self.sp_model = SentencePieceProcessor(model_file=model_path)
+        logger.info(f"Reloaded SentencePiece model from {model_path}")
+
+        # BOS / EOS token IDs
+        self.n_words: int = self.sp_model.vocab_size()
+        self.bos_id: int = self.sp_model.bos_id()
+        self.eos_id: int = self.sp_model.eos_id()
+        self.pad_id: int = self.sp_model.pad_id()
+        logger.info(
+            f"#words: {self.n_words} - BOS ID: {self.bos_id} - EOS ID: {self.eos_id}"
+        )
+        assert self.sp_model.vocab_size() == self.sp_model.get_piece_size()
+
+    def encode(self, s: str, bos: bool, eos: bool) -> List[int]:
+        assert type(s) is str
+        t = self.sp_model.encode(s)
+        if bos:
+            t = [self.bos_id] + t
+        if eos:
+            t = t + [self.eos_id]
+        return t
+
+    def decode(self, t: List[int]) -> str:
+        return self.sp_model.decode(t)
+
+tokenizer = Tokenizer(model_path="botchan.model") # Replace with actual model path