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 votes115 views3 answers
Label encoding column pandas
Python
0 vote162 views1 answer
How to do a mac vendor lookup in python
Python
0 vote146 views1 answer
User passes test django
Python
0 vote162 views1 answer
Remove outliers numpy array
Python
42 votes160 views6 answers
Python regex
Python
0 vote180 views1 answer
Insert single value in dataframe using index
Python
0 vote163 views1 answer
Unable to get local issuer certificate python
Python
0 vote215 views1 answer
Pytest create server
Python
0 vote173 views1 answer
Shebnag python
Python
6 votes162 views1 answer
Python lambda key sort
Python