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

114 votes344 views6 answers
Python print to file
Python
0 vote310 views1 answer
Os file size python
Python
15 votes333 views3 answers
Sum of 2 numbers in python
Python
2 votes331 views1 answer
Python can't subtract offset-naive and offset-aware datetimes
Python
6 votes301 views2 answers
Merge list elements python
Python
0 vote309 views1 answer
WAP which defines and calls a function that receives an octal number and prints the equivalent number bases i.e. in decimal, binary and hexadecimal equivalents.
Python
19 votes326 views6 answers
How to import turtle in python
Python
2 votes268 views1 answer
Discord.py username input in numbers
Python
1 vote476 views2 answers
Django password hashing
Python Django
0 vote363 views3 answers
Flask socketio with gevent
Python