## Model Performance

### Classification Report

| Class     | Precision | Recall | F1-Score | Support |
|-----------|-----------|--------|----------|---------|
| Negative  | 0.90      | 0.89   | 0.90     | 14692   |
| Neutral   | 0.90      | 0.88   | 0.89     | 16970   |
| Positive  | 0.89      | 0.92   | 0.90     | 16861   |

- **Accuracy**: 90%
- **Macro Avg Precision**: 0.90
- **Macro Avg Recall**: 0.90
- **Macro Avg F1-Score**: 0.90

### Summary

This model achieves a balanced performance across all sentiment classes, with high precision and recall, especially in the positive and negative classes.


---
tags:
- text-classification
- sentiment-analysis
pipeline_tag: text-classification
---

# Model Name
ft-Malay-bert

## Model Description
This model is a fine-tuned version of [BERT](https://huggingface.co/bert-base-uncased) for the Malay language. It has been trained on [describe your dataset] to perform [specific task, e.g., sentiment analysis, classification, etc.].

## Intended Uses & Limitations
This model is intended for [describe intended uses]. It should be noted that [mention any limitations or biases].

## How to Use
```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained("rmtariq/ft-Malay-bert")
tokenizer = AutoTokenizer.from_pretrained("rmtariq/ft-Malay-bert")

inputs = tokenizer("Your text here", return_tensors="pt")
outputs = model(**inputs)