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 vote300 views1 answer
Django nested inlines
Python
2 votes282 views2 answers
Change the color of the button on hovering tkinter
Python
0 vote275 views1 answer
How to usepygame.sprite.spritecollide
Python
-1 vote272 views1 answer
Class views django slug
Python
0 vote311 views1 answer
Mylist = [“hello”, “bye”,”see ya”,”later”] phrase = mylist[1]
Python
3 votes251 views2 answers
Copy a 2d array in python
Python
0 vote288 views1 answer
Preserve leading zeros python
Python
59 votes274 views6 answers
How to get current date and time in python
Python
4 votes298 views3 answers
Astype float across columns pandas
Python
0 vote273 views1 answer
Mount gdrive in pyton
Python