import torch
from transformers import AutoTokenizer
from huggingface_hub import hf_hub_download
from model_utils import MultiTaskXLMR

# Load model
model_path = hf_hub_download("{repo_id_multilingual}", "pytorch_model.bin")
model = MultiTaskXLMR(model_name="xlm-roberta-large", num_intents=5)
model.load_state_dict(torch.load(model_path))
model.eval()

# Inference in any supported language
tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-large")
text = "Tu es un idiot!"  # French
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)

with torch.no_grad():
    tox_logits, _ = model(inputs['input_ids'], inputs['attention_mask'])
    tox_prob = torch.sigmoid(tox_logits).item()
    print(f"Toxicity: {tox_prob:.4f}")

License

MIT

pshashid/xlmr-toxicity-multilingual

XLM-RoBERTa Toxicity Detection (Multilingual)

Overview

Supported Languages

Model Details

Per-Language Performance (F1-Score)

Usage

License

pshashid/
xlmr-toxicity-multilingual