MCPcopy Create free account
hub / github.com/THUDM/GLM / encode

Method encode

data_utils/tokenization_gpt2.py:269–270  ·  view source on GitHub ↗
(self, text)

Source from the content-addressed store, hash-verified

267 return tokens
268
269 def encode(self, text):
270 return self.convert_tokens_to_ids(self.tokenize(text))
271
272 def decode(self, tokens):
273 text = ''.join([self.decoder[token] for token in tokens])

Callers 1

tokenizeMethod · 0.45

Calls 2

convert_tokens_to_idsMethod · 0.95
tokenizeMethod · 0.95

Tested by

no test coverage detected