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 vote113 views1 answer
Dtype cannot be bool python
Python
15 votes122 views2 answers
How to get user ip in python
Python
0 vote147 views1 answer
App = Flask(_name_) NameError: name '_name_' is not defined
Python Flask
0 vote116 views1 answer
Delete all historical data django simple history
Python
0 vote107 views1 answer
Slayer_coins_spent
Python
1 vote65 views1 answer
Google colab power level
Python
0 vote113 views1 answer
Python random phone number
Python
38 votes113 views3 answers
Pil python install
Python
0 vote127 views1 answer
Python get focused window
Python
0 vote123 views1 answer
Numpy random.permutation
Python