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 vote170 views1 answer
Python open file relative to module
Python
2 votes166 views1 answer
Django empty queryset
Python
1 vote150 views1 answer
Complete the function digits(n) that returns how many digits the number has.
Python
25 votes156 views3 answers
Store all files name in a folder python
Python
15 votes156 views2 answers
Python make api request
Python
0 vote166 views1 answer
How to group multiple test in pytest
Python
3 votes182 views1 answer
Python initialize multidimensional list
Python
1 vote167 views1 answer
Python run 2 functions at the same time
Python
0 vote183 views1 answer
Tick size colorbar python
Python
0 vote258 views1 answer
Python tableau a 2 dimensions
Python