somewhere ~20 hours later

tokenizer.py

@@ -0,0 +1,40 @@
+# Taken from llama code and lightly modified
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# This software may be used and distributed according to the terms of the Llama 2 Community License Agreement.
+
+import os
+from logging import getLogger
+from typing import List
+
+from sentencepiece import SentencePieceProcessor
+
+TOKENIZER_MODEL = "tokenizer.model" # the llama sentencepiece tokenizer model
+
+class Tokenizer:
+    def __init__(self):
+        model_path = TOKENIZER_MODEL
+        assert os.path.isfile(model_path), model_path
+        self.sp_model = SentencePieceProcessor(model_file=model_path)
+        print(f"Loaded 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()
+        print(
+            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)