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 vote237 views1 answer
Django foreign key error Cannot assign must be a instance
Python
0 vote249 views1 answer
Networkx select edge
Python
0 vote255 views1 answer
Figure in matplotlib
Python
0 vote271 views1 answer
Python clear stdout
Python
4 votes261 views1 answer
Find text between two strings regex python
Python
0 vote266 views1 answer
Clear variable jupyter notebook
Python
4 votes248 views2 answers
Is python easy or hard to learn
Python
5 votes247 views1 answer
Get text selenium
Python
0 vote269 views1 answer
Groupby Fiscal year
Python
9 votes288 views1 answer
How to save image opencv
Python