# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("yseop/SMM4H2024_Task1_roberta")
model = AutoModelForTokenClassification.from_pretrained("yseop/SMM4H2024_Task1_roberta")Quick Links
SMM4H-2024 Task 1: Adverse Drug Events Detection
Overview
This is a NER model created by fine-tuning FacebookAI/roberta-base on SMM4H 2024 Task 1 corpus.
Results
| F1-Norm | 40 |
| P-Norm | 39.6 |
| R-Norm | 40.4 |
| F1-NER | 47.2 |
| P-NER | 47 |
| R-NER | 47.5 |
| F1-Norm-Unseen | 29.5 |
| P-Norm-Unseen | 23.2 |
| R-Norm-Unseen | 40.6 |
- Downloads last month
- 3
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="yseop/SMM4H2024_Task1_roberta")