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

3 votes187 views1 answer
No module named 'django.core.urlresolvers'
Python
14 votes190 views1 answer
Export a dataframe to excel pandas
Python
1 vote157 views3 answers
Dfs algorithm
Python
3 votes194 views1 answer
How to find the number of times a number appears in python
Python
0 vote124 views1 answer
How to use constructor of base class in derived class in python
Python
0 vote179 views1 answer
Def areEquallyStrong(yourLeft, yourRight, friendsLeft, friendsRight):python execution
Python
0 vote216 views1 answer
Djangodebug toolbar not showing
Python Django
6 votes189 views2 answers
Isnumeric
Python
0 vote238 views1 answer
Python create empty dictionary with keys
Python
0 vote197 views1 answer
Python instagram login
Python