Update README: declare pipeline_tag + PEFT tags for Inference API
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
- tl
|
| 5 |
license: apache-2.0
|
| 6 |
+
tags:
|
| 7 |
+
- text-classification
|
| 8 |
+
- xlm-roberta
|
| 9 |
+
- peft
|
| 10 |
+
- lora
|
| 11 |
+
- sentiment-analysis
|
| 12 |
+
pipeline_tag: text-classification
|
| 13 |
+
base_model: FacebookAI/xlm-roberta-base
|
| 14 |
---
|
| 15 |
+
|
| 16 |
+
# XLM-RoBERTa Rise On AI — Sentiment Analysis
|
| 17 |
+
|
| 18 |
+
Fine-tuned XLM-RoBERTa (LoRA) for Filipino/English/Taglish 3-class sentiment.
|
| 19 |
+
|
| 20 |
+
**Labels:** positive · negative · distress
|
| 21 |
+
**Accuracy:** 82.6% · **F1 macro:** 0.815
|
| 22 |
+
|
| 23 |
+
## Usage
|
| 24 |
+
|
| 25 |
+
```python
|
| 26 |
+
from transformers import pipeline
|
| 27 |
+
clf = pipeline('text-classification', model='cjcastro/xlm-roberta-Rise-On-AI', top_k=None)
|
| 28 |
+
print(clf('I feel happy today!'))
|
| 29 |
+
```
|