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 votes495 views4 answers
Python how to count items in array
Python
1 vote199 views1 answer
Convert list of values to dictionary based on count
Python
4 votes214 views4 answers
Recursion python examples
Python
1 vote190 views1 answer
Make a message appear after specified Time python
Python
16 votes202 views4 answers
List to dataframe columns
Python
0 vote186 views1 answer
Mat.at(row,col) Opencv
Python
0 vote192 views1 answer
"_tkinter.TclError: bad entry index "1.0""
Python
0 vote203 views1 answer
Get all commands discord.py
Python
0 vote211 views1 answer
Firebase python flask
Python Flask
1 vote198 views1 answer
Discord python command alias
Python