MCPcopy Create free account
hub / github.com/MiniMax-AI/VTP / encode

Method encode

vtp/tokenizers/text_tokenizer.py:250–257  ·  view source on GitHub ↗

Encode text to token IDs.

(self, text)

Source from the content-addressed store, hash-verified

248 return word
249
250 def encode(self, text):
251 """Encode text to token IDs."""
252 bpe_tokens = []
253 text = self.clean_fn(text)
254 for token in re.findall(self.pat, text):
255 token = ''.join(self.byte_encoder[b] for b in token.encode('utf-8'))
256 bpe_tokens.extend(self.encoder[bpe_token] for bpe_token in self.bpe(token).split(' '))
257 return bpe_tokens
258
259 def decode(self, tokens):
260 """Decode token IDs to text."""

Callers 1

__call__Method · 0.95

Calls 1

bpeMethod · 0.95

Tested by

no test coverage detected