bert-base-sst-nlp-2 / README.md
uvamba's picture
Upload latest checkpoint with model card
0207b5a

Model Card for BERT-base Sentiment Analysis Model

Model Details

This model is a fine-tuned version of BERT-base for sentiment analysis tasks.

Training Data

The model was trained on the Rotten Tomatoes dataset.

Training Procedure

  • Learning Rate: 2e-5
  • Epochs: 3
  • Batch Size: 16 ๊ฐ€๋Šฅํ•˜๋ฉด ๋‹ค๋ฅธ ์‚ฌ๋žŒ๋“ค๋„ ๋˜‘๊ฐ™์€ ๋ฒ„ํŠธ๋ชจ๋ธ, ๋กœํŠผ ํ† ๋ฉ”ํ† ๋ฅผ ์ด์šฉํ–ˆ์„ ๋•Œ ์žฌํ˜„๊ฐ€๋Šฅํ•˜๋„๋ก ํ•˜๋Š” ๋ชจ๋“  ํ•˜์ดํผ ํŒŒ๋ผ๋ฏธํ„ฐ๋“ค์„ ๋‹ค ์ ์–ด๋ผ

How to Use ํ—ˆ๊น… ํŽ˜์ด์Šค ์“ธ ๋•Œ ์–ด๋–ค ๊ฒƒ์„ ์“ฐ๋ฉด ๋œ๋‹ค๋Š” ๊ฑธ ์•Œ๋ ค์ฃผ๋Š” ๊ฒƒ

from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
model = AutoModelForSequenceClassification.from_pretrained("bert-base-uncased")

input_text = "The movie was fantastic with a gripping storyline!"
inputs = tokenizer.encode(input_text, return_tensors="pt")
outputs = model(inputs)
print(outputs.logits)

Evaluation ํ‰๊ฐ€ ๊ฒฐ๊ณผ

  • Accuracy: 81.97%

Limitations ์•ฝ์ ์€ ๋ญ๊ฐ€ ์žˆ๋‹ค๋Š” ๊ฒƒ

The model may generate biased or inappropriate content due to the nature of the training data. It is recommended to use the model with caution and apply necessary filters.

Ethical Considerations

  • Bias: The model may inherit biases present in the training data.
  • Misuse: The model can be misused to generate misleading or harmful content.

Copyright and License

This model is licensed under the MIT License.