DistilBERT IMDb Sentiment Analysis

DistilBERT๋ฅผ IMDb ์˜ํ™” ๋ฆฌ๋ทฐ ๊ฐ์ •๋ถ„์„ ๋ฐ์ดํ„ฐ์…‹์œผ๋กœ fine-tuningํ•œ ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค.

ํ•™์Šต ์ƒ์„ธ

  • ๋ฒ ์ด์Šค ๋ชจ๋ธ: distilbert-base-uncased
  • ๋ฐ์ดํ„ฐ์…‹: IMDb (train 2,000 / test 500 ์ƒ˜ํ”Œ)
  • ํƒœ์Šคํฌ: ์ด์ง„ ๊ฐ์ •๋ถ„๋ฅ˜ (๊ธ์ •/๋ถ€์ •)
  • Epoch: 2
  • Learning Rate: 2e-5
  • Batch Size: 16
  • Max Length: 256

์‚ฌ์šฉ๋ฒ•

from transformers import pipeline

classifier = pipeline("text-classification", model="AutoBot000/distilbert-imdb-sentiment")
result = classifier("This movie was absolutely fantastic!")
print(result)

ํ•œ๊ณ„

  • ํ•™์Šต ๋ฐ์ดํ„ฐ๋ฅผ 2,000๊ฐœ๋กœ ์ถ•์†Œํ•˜์—ฌ ์‹ค์Šต ๋ชฉ์ ์œผ๋กœ ํ•™์Šตํ•จ
  • ์ „์ฒด ๋ฐ์ดํ„ฐ(25K)๋กœ ํ•™์Šต ์‹œ ์„ฑ๋Šฅ ํ–ฅ์ƒ ๊ธฐ๋Œ€
  • ์˜์–ด ๋ฆฌ๋ทฐ ์ „์šฉ
Downloads last month
30
Safetensors
Model size
67M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for AutoBot000/distilbert-imdb-sentiment

Finetuned
(10944)
this model

Dataset used to train AutoBot000/distilbert-imdb-sentiment