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

-2 votes187 views1 answer
Requests.exceptions.connectionerror: ('connection aborted.', remotedisconnected('remote end closed connection without response'))
Python
75 votes151 views2 answers
Httpie on windows
Python
-2 votes174 views4 answers
DFS
Python
114 votes166 views5 answers
How to use inputs in python
Python
1 vote171 views1 answer
How todelete a line in python
Python
-1 vote179 views9 answers
Django for Beginners
Python
3 votes199 views2 answers
Discord.py make command admin only
Python
0 vote195 views1 answer
Pyttsx3 NameError: name 'voices' is not defined
Python
1 vote214 views1 answer
Django how to set a navbar active
Python Django
6 votes227 views2 answers
How to check if django is installed( in python shell)
Python Django