README.md

---
tags:
- roberta
library_name: peft
datasets:
- rotten_tomatoes
pipeline_tag: text-classification

---

# Adapter `solwol/roberta-sentiment-classifier-peft` for roberta-base

<!-- PERT adapter for sentiment-classification. -->

## Usage

First, install `transformers` and `peft`:

```
pip install -U transformers peft
```

Now, the peft adapter can be loaded and activated like this:

```python
from peft import PeftModel, PeftConfig
from transformers import AutoModelForSequenceClassification, RobertaConfig

config = RobertaConfig.from_pretrained(
    "roberta-base",
    id2label={0: "👎", 1: "👍"}
)
model = AutoModelForSequenceClassification.from_pretrained("roberta-base", config=config)
model = PeftModel.from_pretrained(model, "solwol/roberta-sentiment-classifier-peft")
```

Next, to perform sentiment classification:

```python
from transformers import AutoTokenizer, TextClassificationPipeline

tokenizer = AutoTokenizer.from_pretrained("roberta-base")
classifier = TextClassificationPipeline(model=model, tokenizer=tokenizer)
classifier("This is awesome!")
[{'label': '👍', 'score': 0.9765560626983643}]
```