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 vote181 views1 answer
R vs python
Python
0 vote146 views1 answer
Python: if null give a value if not null concatenate
Python
0 vote150 views1 answer
Start models
Python
13 votes190 views2 answers
How to know how much lines a file has using python
Python
5 votes146 views3 answers
Python is not
Python
0 vote141 views3 answers
Dataframe to dictionary using index as key
Python
0 vote136 views1 answer
Como fazer um bot spamm no discord com python
Python
22 votes129 views3 answers
Python except error as e
Python
2 votes132 views2 answers
How to split a list to 1000 items python
Python
1 vote125 views2 answers
Python write json to file utf8
Python