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

1 vote145 views1 answer
Get device name tensorflow
Python
6 votes164 views5 answers
No module named env.__main__; 'env' is a package and cannot be directly executed
Python
7 votes140 views3 answers
Np array to df
Python
0 vote142 views1 answer
How to read PDF from link in Python]
Python
5 votes147 views3 answers
Pygame quit
Python
7 votes148 views4 answers
Jupyter notebook plot larger
Python
63 votes149 views6 answers
What is a class in python
Python
-1 vote146 views1 answer
Pandas datetime show only date
Python
1 vote103 views1 answer
Format listto string pytthon
Python
1 vote153 views1 answer
Frequency of occurrence of that element in the list and the positions
Python