Sentiment Analysis Models
Collection
Collection of XLM-R-based Sentiment Analysis models trained on the data with two labels - positive and negative.
•
25 items
•
Updated
YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Fine-tuned XLM-R Model for romanian Sentiment Analysis
This is a fine-tuned XLM-R model for sentiment analysis in romanian.
Model Details
- Model Name: XLM-R Sentiment Analysis
- Language: romanian
- Fine-tuning Dataset: DGurgurov/romanian_sa
Training Details
- Epochs: 20
- Batch Size: 32 (train), 64 (eval)
- Optimizer: AdamW
- Learning Rate: 5e-5
Performance Metrics
- Accuracy: 0.94167
- Macro F1: 0.94166
- Micro F1: 0.94167
Usage
To use this model, you can load it with the Hugging Face Transformers library:
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("DGurgurov/xlm-r_romanian_sentiment")
model = AutoModelForSequenceClassification.from_pretrained("DGurgurov/xlm-r_romanian_sentiment")
License
[MIT]
- Downloads last month
- 165
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.