MCPcopy Index your code
hub / github.com/zai-org/CodeGeeX / encode_code

Method encode_code

codegeex/tokenizer/tokenizer.py:51–56  ·  view source on GitHub ↗
(self, code: str)

Source from the content-addressed store, hash-verified

49 self.eos_token_id = self.tokenizer.eos_token_id
50
51 def encode_code(self, code: str):
52 if self.mode == 'codegeex-13b':
53 code = encode_whitespaces(code, self.start_extra_id, self.max_len)
54 input_ids = self.tokenizer(code, is_split_into_words=False, verbose=False).input_ids
55
56 return input_ids
57
58 def decode_code(self, input_ids):
59 if self.mode == 'codegeex-13b':

Callers 3

mainFunction · 0.95
mainFunction · 0.95
generateFunction · 0.45

Calls 1

encode_whitespacesFunction · 0.70

Tested by 2

mainFunction · 0.76
mainFunction · 0.76