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 vote182 views1 answer
Decreasing for loop python
Python
13 votes203 views2 answers
How to copy one dictionary to another in python
Python
0 vote185 views1 answer
Add option in python script
Python
-1 vote245 views3 answers
Open csv from url python
Python
0 vote184 views1 answer
Pandas parameters read
Python
10 votes186 views4 answers
Multiply each element in list python
Python
7 votes177 views2 answers
Traceback python
Python
3 votes201 views2 answers
Getting text input pygame python
Python
1 vote193 views1 answer
Sftp python
Python
11 votes183 views1 answer
Python discord
Python