---
language: en
license: apache-2.0
tags:
  - masked-language-modeling
  - imdb
  - distilbert
  - domain-adaptation
  - tensorflow
  - movie-reviews
pipeline_tag: fill-mask
widget:
  - text: "This movie was absolutely [MASK]."
---

# distilbert-base-uncased-finetuned-imdb

This is a **DistilBERT** model fine-tuned using **Masked Language Modeling (MLM)** on the **IMDB movie reviews dataset**.  
It is domain-adapted specifically for understanding and completing movie-related text.

---

## Model Details

- **Base model**: [`distilbert-base-uncased`](https://huggingface.co/distilbert-base-uncased)
- **Training objective**: Masked Language Modeling
- **Domain**: English movie reviews (IMDB)
- **Framework**: TensorFlow / Keras
- **Training time**: ~3 hours on Google Colab
- **Chunk size**: 128 tokens

---

## Use Case

This model is ideal for:
- Autocompletion of masked tokens in movie reviews
- Domain-aware masked language modeling
- Sentence generation or augmentation in film-related contexts

---

## Example Usage

```python
from transformers import pipeline

fill_mask = pipeline(
    "fill-mask",
    model="Prathamesh2403/distilbert-base-uncased-finetuned-imdb",
    tokenizer="Prathamesh2403/distilbert-base-uncased-finetuned-imdb"
)

fill_mask("This movie was absolutely [MASK].")