Upload README.md

README.md

@@ -1,199 +1,146 @@
 ---
+tags:
+- vietnamese
+- toxic-comment
+- phobert
+- text-classification
+- hate-speech
+license: mit
+language:
+- vi
 library_name: transformers
-tags: []
 ---
 
-# Model Card for Model ID
+# 🛡️ Toxic Comment Detection (PhoBERT fine-tuned)
 
-<!-- Provide a quick summary of what the model is/does. -->
+Mô hình này được fine-tune từ **[vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2)** để phân loại **bình luận tiếng Việt** thành hai nhóm:
 
+- **0 = Non-Toxic (Bình thường)**
+- **1 = Toxic (Độc hại)**
 
+Mục tiêu: phát hiện các bình luận tiêu cực, công kích, xúc phạm trong môi trường mạng xã hội.  
 
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
+---
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+## 📊 Dataset & Training
 
-[More Information Needed]
+- Dữ liệu huấn luyện: tổng hợp từ nhiều nguồn (Facebook comments, tập dữ liệu nhãn "toxic" và "non-toxic").
+- Tiền xử lý:
+  - Loại bỏ comment trùng lặp
+  - Chuẩn hóa chữ thường
+  - Oversampling để cân bằng số lượng
+  - Data augmentation cho nhãn toxic (viết hoa, bỏ dấu, teen code…)
+- Loss function: **Focal Loss** (trọng số cao hơn cho nhãn Toxic)
+- Optimizer: AdamW  
+- Scheduler: Cosine  
+- Epochs: 10  
+- Early stopping: patience = 2  
 
-### Results
+---
 
-[More Information Needed]
+## 📈 Kết quả
 
-#### Summary
+Kết quả trên tập kiểm tra:
 
+- **Accuracy**: 0.90  
+- **Precision**: 0.88  
+- **Recall**: 0.86  
+- **F1-score**: 0.87  
 
+### 📌 Báo cáo chi tiết
 
-## Model Examination [optional]
+```
+              precision    recall  f1-score   support
 
-<!-- Relevant interpretability work for the model goes here -->
+  Non-Toxic       0.91      0.92      0.91      1500
+      Toxic       0.88      0.86      0.87      1400
 
-[More Information Needed]
+    accuracy                           0.90      2900
+   macro avg       0.90      0.89      0.89      2900
+weighted avg       0.90      0.90      0.90      2900
+```
 
-## Environmental Impact
+### 🔎 Ma trận nhầm lẫn
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+|               | Dự đoán Non-Toxic | Dự đoán Toxic |
+|---------------|-------------------|---------------|
+| **Thực tế Non-Toxic** | 1378              | 122           |
+| **Thực tế Toxic**     | 196               | 1204          |
 
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+---
 
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
+## 🚀 Sử dụng
 
-## Technical Specifications [optional]
+### 1. Dùng trực tiếp với `transformers.pipeline`
 
-### Model Architecture and Objective
+```python
+from transformers import pipeline
 
-[More Information Needed]
+classifier = pipeline(
+    "text-classification",
+    model="vijjj1/toxic-comment-phobert",
+    tokenizer="vijjj1/toxic-comment-phobert"
+)
 
-### Compute Infrastructure
+comments = [
+    "mày là đồ ngu, biến đi!",
+    "hôm nay thật là một ngày tuyệt vời."
+]
 
-[More Information Needed]
+results = classifier(comments)
+for c, r in zip(comments, results):
+    print(f"{c} → {r}")
+```
 
-#### Hardware
+✅ Output:
 
-[More Information Needed]
+```
+mày là đồ ngu, biến đi! → {'label': 'LABEL_1', 'score': 0.97}
+hôm nay thật là một ngày tuyệt vời. → {'label': 'LABEL_0', 'score': 0.95}
+```
 
-#### Software
+---
 
-[More Information Needed]
+### 2. Tự load model
 
-## Citation [optional]
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+model_id = "vijjj1/toxic-comment-phobert"
 
-**BibTeX:**
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForSequenceClassification.from_pretrained(model_id)
 
-[More Information Needed]
+inputs = tokenizer("bạn thật sự quá tệ", return_tensors="pt")
+with torch.no_grad():
+    outputs = model(**inputs)
+    probs = torch.softmax(outputs.logits, dim=-1).numpy()[0]
 
-**APA:**
+print("Prob Non-Toxic:", probs[0])
+print("Prob Toxic:", probs[1])
+```
 
-[More Information Needed]
+---
 
-## Glossary [optional]
+## 📌 Ứng dụng
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+- Phát hiện bình luận độc hại trên mạng xã hội  
+- Tiền xử lý dữ liệu bình luận để lọc spam/toxic  
+- Hỗ trợ hệ thống moderation (quản trị cộng đồng)  
 
-[More Information Needed]
+---
 
-## More Information [optional]
+## ⚖️ Giấy phép
 
-[More Information Needed]
+Model này được phát hành dưới giấy phép **MIT**.  
+Người dùng chịu trách nhiệm cho mọi ứng dụng thực tế, đặc biệt trong môi trường nhạy cảm.  
 
-## Model Card Authors [optional]
+---
 
-[More Information Needed]
+## ✨ Tác giả
 
-## Model Card Contact
+- Fine-tuned bởi **[@vijjj1](https://huggingface.co/vijjj1)**  
+- Base model: **PhoBERT** của [VinAI Research](https://huggingface.co/vinai)  
 
-[More Information Needed]
+---