Promptzl
v1.0.0
Ubah LLMS canggih menjadi nol + -shot pytorch classifiers hanya dalam beberapa baris kode.
Penawaran Promptzl:
Untuk informasi lebih lanjut, lihat dokumentasi resmi .
pip install -U promptzl
Hanya dalam beberapa baris kode, Anda dapat mengubah LLM pilihan menjadi classifier jadul dengan semua properti yang diinginkan:
Siapkan dataset:
from datasets import Dataset
dataset = Dataset . from_dict (
{
'text' : [
"The food was absolutely wonderful, from preparation to presentation, very pleasing." ,
"The service was a bit slow, but the food made up for it. Highly recommend the pasta!" ,
"The restaurant was too noisy and the food was mediocre at best. Not worth the price." ,
],
'label' : [ 1 , 1 , 0 ]
}
)Tentukan prompt untuk memandu model bahasa ke prediksi yang benar:
from promptzl import FnVbzPair , Vbz
prompt = FnVbzPair (
lambda e : f"""Restaurant review classification into categories 'positive' or 'negative'.
'Best pretzls in town!'='positive'
'Rude staff, horrible food.'='negative'
' { e [ 'text' ] } '=""" ,
Vbz ({ 0 : [ "negative" ], 1 : [ "positive" ]}))Inisialisasi model:
from promptzl import CausalLM4Classification
model = CausalLM4Classification (
'HuggingFaceTB/SmolLM2-1.7B' ,
prompt = prompt )Klasifikasi data:
from sklearn . metrics import accuracy_score
output = model . classify ( dataset , show_progress_bar = True , batch_size = 1 )
accuracy_score ( dataset [ 'label' ], output . predictions )
1.0Untuk tutorial lebih rinci, lihat dokumentasi!