visolex / mbert-hsd

huggingface.co
Total runs: 12
24-hour runs: 0
7-day runs: 0
30-day runs: 2
Model's Last Updated: January 05 2026
text-classification

Introduction of mbert-hsd

Model Details of mbert-hsd

MBERT

mBERT fine-tuned cho bài toán phân loại Hate Speech tiếng Việt.

Model Details
  • Model type : Fine-tuned transformer model
  • Architecture : mBERT (Multilingual BERT)
  • Base model : bert-base-multilingual-cased
  • Task : Hate Speech Classification
  • Language : Vietnamese
  • Labels : CLEAN (0), OFFENSIVE (1), HATE (2)
📊 Model Performance
Metric Score
Accuracy 0.9360
F1 Macro 0.8044
F1 Weighted 0.9317
Model Description

mBERT fine-tuned cho bài toán phân loại Hate Speech tiếng Việt. Model này được fine-tune từ bert-base-multilingual-cased trên dataset ViHSD (Vietnamese Hate Speech Dataset).

How to Use
Basic Usage
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

# Load model and tokenizer
model_name = "visolex/hate-speech-mbert"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# Classify text
text = "Văn bản tiếng Việt cần phân loại"
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)

with torch.no_grad():
    outputs = model(**inputs)
    predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
    predicted_label = torch.argmax(predictions, dim=-1).item()

# Label mapping
label_names = {
    0: "CLEAN",
    1: "OFFENSIVE",
    2: "HATE"
}

print(f"Predicted label: {label_names[predicted_label]}")
print(f"Confidence scores: {predictions[0].tolist()}")
Using the Pipeline
from transformers import pipeline

classifier = pipeline(
    "text-classification",
    model="visolex/hate-speech-mbert",
    tokenizer="visolex/hate-speech-mbert"
)

result = classifier("Văn bản tiếng Việt cần phân loại")
print(result)
Training Details
Training Data
  • Dataset: ViHSD (Vietnamese Hate Speech Dataset)
  • Training samples: ~8,000 samples
  • Validation samples: ~1,000 samples
  • Test samples: ~1,000 samples
Training Procedure
  • Framework: PyTorch + Transformers
  • Optimizer: AdamW
  • Learning Rate: 2e-5
  • Batch Size: 32
  • Epochs: Varies by model
  • Max Sequence Length: 256
Label Distribution
  • CLEAN (0): Normal content without offensive language
  • OFFENSIVE (1): Mildly offensive content
  • HATE (2): Hate speech and extremist language
Evaluation

Model được đánh giá trên test set của ViHSD với các metrics:

  • Accuracy: Overall classification accuracy
  • F1 Macro: Macro-averaged F1 score across all labels
  • F1 Weighted: Weighted F1 score based on label frequency
Limitations and Bias
  • Model chỉ được train trên dữ liệu tiếng Việt từ mạng xã hội
  • Performance có thể giảm trên domain khác (email, document, etc.)
  • Model có thể có bias từ dữ liệu training
  • Cần đánh giá thêm trên dữ liệu real-world
Citation
Contact
License

This model is distributed under the MIT License.

Runs of visolex mbert-hsd on huggingface.co

12
Total runs
0
24-hour runs
1
3-day runs
0
7-day runs
2
30-day runs

More Information About mbert-hsd huggingface.co Model

More mbert-hsd license Visit here:

https://choosealicense.com/licenses/mit

mbert-hsd huggingface.co

mbert-hsd huggingface.co is an AI model on huggingface.co that provides mbert-hsd's model effect (), which can be used instantly with this visolex mbert-hsd model. huggingface.co supports a free trial of the mbert-hsd model, and also provides paid use of the mbert-hsd. Support call mbert-hsd model through api, including Node.js, Python, http.

mbert-hsd huggingface.co Url

https://huggingface.co/visolex/mbert-hsd

visolex mbert-hsd online free

mbert-hsd huggingface.co is an online trial and call api platform, which integrates mbert-hsd's modeling effects, including api services, and provides a free online trial of mbert-hsd, you can try mbert-hsd online for free by clicking the link below.

visolex mbert-hsd online free url in huggingface.co:

https://huggingface.co/visolex/mbert-hsd

mbert-hsd install

mbert-hsd is an open source model from GitHub that offers a free installation service, and any user can find mbert-hsd on GitHub to install. At the same time, huggingface.co provides the effect of mbert-hsd install, users can directly use mbert-hsd installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

mbert-hsd install url in huggingface.co:

https://huggingface.co/visolex/mbert-hsd

Url of mbert-hsd

mbert-hsd huggingface.co Url

Provider of mbert-hsd huggingface.co

visolex
ORGANIZATIONS

Other API from visolex

huggingface.co

Total runs: 91
Run Growth: 34
Growth Rate: 37.36%
Updated:January 05 2026
huggingface.co

Total runs: 47
Run Growth: 29
Growth Rate: 60.42%
Updated:January 05 2026
huggingface.co

Total runs: 37
Run Growth: 4
Growth Rate: 11.11%
Updated:January 05 2026
huggingface.co

Total runs: 35
Run Growth: -18
Growth Rate: -52.94%
Updated:January 05 2026
huggingface.co

Total runs: 27
Run Growth: 22
Growth Rate: 84.62%
Updated:January 05 2026
huggingface.co

Total runs: 21
Run Growth: 2
Growth Rate: 9.52%
Updated:June 20 2025
huggingface.co

Total runs: 16
Run Growth: 9
Growth Rate: 52.94%
Updated:January 05 2026
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:October 17 2025
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:October 29 2025