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 vote162 views2 answers
Numpy split to chunks of equal size
Python
0 vote159 views2 answers
Python time a code segment
Python
17 votes161 views4 answers
Python pil resize image
Python
0 vote192 views1 answer
Suppress pandas future warnings
Python
0 vote182 views1 answer
Difference in django project view and app view
Python
0 vote157 views1 answer
Find pdf encrypted password with python
Python
0 vote143 views1 answer
Discord.py - change the default help command
Python
0 vote154 views1 answer
Select numbers from a list with a limit python
Python
16 votes170 views3 answers
Python gitignore
Python
1 vote176 views1 answer
Select certain element from ndarray python
Python