Create README.md

README.md

@@ -0,0 +1,59 @@
+---
+language: vi
+tags:
+- spam-detection
+- vietnamese
+- bartpho
+license: apache-2.0
+datasets:
+- visolex/ViSpamReviews
+metrics:
+- accuracy
+- f1
+model-index:
+- name: bartpho-spam-classification
+  results:
+  - task:
+      type: text-classification
+      name: Spam Detection (Multi-Class)
+    dataset:
+      name: ViSpamReviews
+      type: custom
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: <INSERT_ACCURACY>
+    - name: F1 Score
+      type: f1
+      value: <INSERT_F1_SCORE>
+base_model:
+- vinai/bartpho-syllable
+pipeline_tag: text-classification
+---
+
+# BARTPho-Spam-MultiClass
+
+Fine-tuned from [`vinai/bartpho-syllable`](https://huggingface.co/vinai/bartpho-syllable) on **ViSpamReviews** (multi-class).
+
+* **Task**: 4-way classification
+* **Dataset**: [ViSpamReviews](https://huggingface.co/datasets/visolex/ViSpamReviews)
+* **Hyperparameters**
+
+  * Batch size: 32
+  * LR: 3e-5
+  * Epochs: 100
+  * Max seq len: 256
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+tokenizer = AutoTokenizer.from_pretrained("visolex/bartpho-spam-classification")
+model = AutoModelForSequenceClassification.from_pretrained("visolex/bartpho-spam-classification")
+
+text = "Đánh giá quá chung chung, không liên quan."
+inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=256)
+pred = model(**inputs).logits.argmax(dim=-1).item()
+label_map = {0: "NO-SPAM",1: "SPAM-1",2: "SPAM-2",3: "SPAM-3"}
+print(label_map[pred])
+```