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 vote289 views1 answer
Python check if two sets intersect
Python
2 votes304 views1 answer
Python hashlib.sha512()
Python
2 votes306 views3 answers
Marks input using list in python
Python
0 vote304 views1 answer
Pyqt5 python how to add a widgtet to a table
Python
0 vote328 views1 answer
Tar dataset
Python
4 votes304 views2 answers
Python replace by dictionary
Python
16 votes279 views4 answers
Python check list contains another list
Python
0 vote257 views1 answer
Nested dictionary to dataframe
Python
0 vote307 views1 answer
Kivy bind when text changes
Python
13 votes297 views2 answers
Ipykernel install
Python