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 vote230 views1 answer
Fomat json load python
Python
0 vote224 views2 answers
Python multiply 2 variables
Python
1 vote189 views1 answer
Torch concat two 1d tensor
Python
0 vote232 views1 answer
Pyspark case when
Python
1 vote251 views6 answers
Add item to tuple python
Python
0 vote225 views1 answer
Calculer un temps en python
Python
-1 vote184 views1 answer
Import url
Python
13 votes303 views1 answer
Flask app starter
Python Flask
2 votes225 views1 answer
Get list of all files in folder and subfolders python
Python
0 vote219 views1 answer
Python write error to file
Python