Text Classification
Transformers
Safetensors
English
distilbert
sentiment-analysis
imdb
text-embeddings-inference
Instructions to use andrewczl/distilbert-imdb-sentiment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use andrewczl/distilbert-imdb-sentiment with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="andrewczl/distilbert-imdb-sentiment")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("andrewczl/distilbert-imdb-sentiment") model = AutoModelForSequenceClassification.from_pretrained("andrewczl/distilbert-imdb-sentiment", device_map="auto") - Notebooks
- Google Colab
- Kaggle
DistilBERT IMDB Sentiment
Modello DistilBERT fine-tuned per classificazione binaria del sentiment su recensioni IMDB.
Dati
- Dataset: IMDB
- Training subset: 2000 esempi
- Test/validation subset: 500 esempi
- Seed: 42
Training
- Modello base: distilbert-base-uncased
- Learning rate: 3e-5
- Epoche: 3
Metriche
- Validation accuracy: 0.878
- Eval loss: 0.296265
Limiti
Il modello è stato addestrato su un sottoinsieme ridotto del dataset IMDB e su recensioni in inglese, quindi i risultati non sono rappresentativi dell'intero dataset o di testi in altre lingue.
- Downloads last month
- 73