MCPcopy Create free account
hub / github.com/togethercomputer/OpenChatKit / build_tokenizer

Function build_tokenizer

training/modules/tokenizer.py:4–8  ·  view source on GitHub ↗
(args)

Source from the content-addressed store, hash-verified

2from transformers import AutoTokenizer, GPT2TokenizerFast, DebertaV2Tokenizer
3
4def build_tokenizer(args):
5 tokenizer = AutoTokenizer.from_pretrained(args.tokenizer_name)
6 if tokenizer.pad_token is None:
7 tokenizer.pad_token = tokenizer.eos_token
8 return tokenizer
9
10def build_gpt2_tokenizer(args):
11 tokenizer = GPT2TokenizerFast.from_pretrained(args.tokenizer_name)

Callers 2

mainFunction · 0.90
mainFunction · 0.90

Calls 1

from_pretrainedMethod · 0.45

Tested by

no test coverage detected