📝 Model Card: bert-imdb-finetuned

🔍 Introduction

The wakaflocka17/bert-imdb-finetuned model is a fine-tuned version of google-bert/bert-base-uncased for the sentiment classification task on the IMDb dataset. Trained on movie reviews, it can distinguish between positive and negative sentiment with excellent accuracy. Below you will find its model card, evaluation metrics, training parameters, and a practical example of its use in Google Colab.

📊 Evaluation Metrics

Metric	Value
Accuracy	0.8734
Precision	0.8661
Recall	0.8834
F1-score	0.8746

⚙️ Training Parameters

Parameter	Values
Modello di base	bert-base-uncased
Repo pretrained	bert-base-uncased
Repo finetuned	models/bert_base_uncased
Repo downloaded	models/downloaded/bert_base_uncased
Epochs	3
Batch size (train)	16
Batch size (eval)	32
Numero di label	2

🚀 Example of use in Colab

Installing dependencies

!pip install --upgrade transformers huggingface_hub

(Optional) Authentication for private models.

from huggingface_hub import login
login(token="hf_yourhftoken")

Loading tokenizer and model

from transformers import AutoTokenizer, AutoModelForSequenceClassification, TextClassificationPipeline

repo_id   = "wakaflocka17/bert-imdb-finetuned"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model     = AutoModelForSequenceClassification.from_pretrained(repo_id)

# Override default labels
model.config.id2label = {0: 'NEGATIVE', 1: 'POSITIVE'}
model.config.label2id = {'NEGATIVE': 0, 'POSITIVE': 1}

# Create the classification pipeline
pipe = TextClassificationPipeline(model=model, tokenizer=tokenizer, return_all_scores=True)

Inference on a text example

testo     = "This movie was absolutely fantastic—wonderful performances and a gripping story!"
risultati = pipe(testo)
print(risultati)
# Es. output:
# [{'label': 'POSITIVE', 'score': 0.95}, {'label': 'NEGATIVE', 'score': 0.05}]

📖 How to cite

If you use this model in your work, you can cite it as:

@misc{Sentiment-Project,
  author       = {Francesco Congiu},
  title        = {Sentiment Analysis with Pretrained, Fine-tuned and Ensemble Transformer Models},
  howpublished = {\url{https://github.com/wakaflocka17/DLA_LLMSANALYSIS}},
  year         = {2025}
}

🔗 Reference Repository

All the file structure and script examples can be found at: https://github.com/wakaflocka17/DLA_LLMSANALYSIS/tree/main