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 vote107 views1 answer
Tkinter sin
Python
0 vote92 views1 answer
Use of numpy matrix in tkinter python 3
Python
7 votes135 views2 answers
Python remove html tags
Python
1 vote114 views2 answers
{:.1%} print one decimal pandas
Python
0 vote118 views1 answer
Pycord discord discordpy get total slash commands and total commands regestered in your bot
Python
4 votes103 views3 answers
Row wise mean pandas
Python
0 vote98 views1 answer
Validationerror django params
Python
0 vote139 views1 answer
Django cms api
Python Django
0 vote99 views1 answer
File "main.py", line 11 if message.author == client.user: ^ IndentationError: expected an indented block
Python
0 vote98 views1 answer
Python scipy put more weight to a set value in curve_fit
Python