[D-76] Understanding background.
IPYNB
paste the train.py on the jupyter notebook and run the code snippet.
train.py
loading the model and dataset should be done in the python file.
Tokenizer
code t5p-220m ; huggingface ;
1
2
3
4
5
6
7
8
9
10
11
from transformers import (
AutoTokenizer,
AutoModelForCausalLM,
Trainer,
TrainingArguments,
)
[...]
TOKENIZER_NAME = "Salesforce/codet5p-220m"
This post is licensed under CC BY 4.0 by the author.