Update README.md

README.md

@@ -1,14 +1,37 @@
+# Fine-tuned BERT for IMDB Sentiment Classification
+
+**Model:** google-bert/bert-base-uncased → fine-tuned on IMDB (binary sentiment)
+
+**Task:** Sequence classification (sentiment analysis)
+
+**Author:** Your Name / @YourHFusername  
+**License:** Apache-2.0 (choose appropriate license)
+
 ---
-{}
----
-# Sentiment Analysis Model (BERT Fine-Tuned on IMDB)
 
-This model is a fine-tuned version of **google-bert/bert-base-uncased** on the **IMDB sentiment classification dataset**.
+## Description
+This is a BERT-base model fine-tuned on the IMDB movie reviews dataset for binary sentiment classification (positive / negative).  
+It accepts raw text and returns a label and confidence score.
 
-## 🧠 Usage
+**Input:** string (movie review)  
+**Output:** dictionary with `label` and `score`. By default the model may return `LABEL_0` and `LABEL_1`.  
+Use the `id2label` mapping below to convert to human-readable labels:  
+- `LABEL_0` → `negative`  
+- `LABEL_1` → `positive`
 
+---
+
+## Example usage
 ```python
 from transformers import pipeline
 
-classifier = pipeline("text-classification", model="ManavDhayeCoder/sentiment-bert")
-classifier("This movie was amazing!")
+clf = pipeline("text-classification", model="YourHFusername/sentiment-bert")
+
+print(clf("I loved this movie!"))
+# [{'label': 'LABEL_1', 'score': 0.998}]
+
+# map to human-readable label
+map = { "LABEL_0": "negative", "LABEL_1": "positive" }
+out = clf("I loved this movie!")[0]
+print(map[out["label"]], out["score"])
+# positive 0.998