Update README.md

README.md

@@ -1,3 +1,96 @@
 ---
 license: mit
+language:
+- vi
+metrics:
+- exact_match
+- f1
+library_name: transformers
+pipeline_tag: question-answering
 ---
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [Tô Hoàng Minh Tiến]
+- **Finetuned from model [optional]:** [xml-roberta-base]
+
+
+<!-- Provide the basic links for the model. -->
+
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+```python
+# Load model directly
+from transformers import AutoTokenizer, TFAutoModelForQuestionAnswering
+
+tokenizer = AutoTokenizer.from_pretrained("Tien-THM/QAVi")
+model = TFAutoModelForQuestionAnswering.from_pretrained("Tien-THM/QAVi")
+
+import numpy as np
+
+def Inference(context, question):
+  encoding = tokenizer(context, question, return_tensors='tf')
+  start_pos = model(encoding).start_logits
+  end_pos = model(encoding).end_logits
+  s = np.argmax(start_pos[0])
+  e = np.argmax(end_pos[0])
+  print(tokenizer.decode(encoding['input_ids'][0][s:e+1]))
+
+question = 'Elon Musk là người nước nào?'
+context = 'Elon Reeve Musk FRS (sinh ngày 28 tháng 6 năm 1971), là một kỹ sư, nhà tài phiệt, nhà phát minh, doanh nhân công nghệ và nhà từ thiện người Mỹ gốc Nam Phi.'
+
+Inference(context, question)
+# Answer: người Mỹ gốc Nam Phi
+```
+
+## Training Details
+
+### Training Data
+
+[using 2 datasets: Zalo Challenge 2022 and XSQUAD Vi]
+
+### Training Procedure 
+
+
+#### Training Hyperparameters
+* Learning rate: 2e-5
+* Batch size: 16
+* Epoch: 4
+
+#### Training Loss
+| Epoch | Train loss | Validation loss | Exact Match |
+|----------|----------|----------|----------|
+| #1 | 3.0424 | 1.3987 | 0.68 |
+| #2 | 0.9563 | 1.2139 | 0.74 |
+| #3 | 0.3920 | 1.4264 | 0.75 |
+| #4 | 0.2175 | 1.4742 | 0.74 |
+I restored the check point in the 2nd epoch
+
+
+## Evaluation
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Metrics
+
+* Exact Match: 0.74
+* F1: 0.84
+
+
+
+