Generate python

from transformers import AutoTokenizer, AutoModelWithLMHead


tokenizer = AutoTokenizer.from_pretrained("Sentdex/GPyT")
model = AutoModelWithLMHead.from_pretrained("Sentdex/GPyT").to("cuda")


def generate(code, max_length=100):
    '''Takes input code, replaces newline chars with <N>, 
    tokenizes, feeds thru model, decodes, 
    then reformats the newlines back in'''
    newlinechar = "<N>"
    converted = code.replace("\n", newlinechar)
    tokenized = tokenizer.encode(converted, return_tensors='pt').to("cuda")
    resp = model.generate(tokenized, max_length=max_length).to("cuda")

    decoded = tokenizer.decode(resp[0])
    reformatted = decoded.replace("<N>","\n")
    return reformatted


print(generate("import"))

Source: pythonprogramming.net

Similar codes

0 vote112 views1 answer
Logistic regresion heart disease python
Python
79 votes111 views6 answers
String reverse in python
Python
0 vote110 views2 answers
Cronometer python
Python
76 votes145 views6 answers
How to iterate through a list in python
Python
0 vote116 views1 answer
Python developer salary
Python
1 vote113 views2 answers
Python print trailing zeros
Python
8 votes115 views1 answer
Python CSV Has No Attribute 'Writer
Python
0 vote106 views2 answers
How do i make a for loop in python
Python
0 vote108 views1 answer
Pixmap in python
Python
2 votes115 views2 answers
Python coding questions and answers
Python