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

11 votes254 views3 answers
Practicing python
Python
6 votes252 views6 answers
Python ide
Python
1 vote272 views1 answer
Par o inpar python
Python
0 vote263 views1 answer
Ejercicios con def en python
Python
0 vote292 views1 answer
Python nth prime function
Python
1 vote254 views2 answers
Getting player input python
Python
-1 vote274 views3 answers
Try using .loc[row_indexer,col_indexer] = value instead
Python
1 vote265 views1 answer
Localhost postgres settings django
Python
0 vote241 views2 answers
How to use information from env variables in python
Python
0 vote261 views1 answer
Why am i not able to import wtf flask
Python