Create README.md

README.md

@@ -0,0 +1,43 @@
+---
+datasets:
+- grammarly/coedit
+- Owishiboo/grammar-correction
+language:
+- en
+base_model:
+- google-t5/t5-base
+pipeline_tag: text-generation
+---
+
+# Quick Start (Python)
+
+### Installation
+```bash
+pip install transformers torch
+```
+
+### Basic Usage
+```python
+from transformers import T5Tokenizer, T5ForConditionalGeneration
+import torch
+
+# Load model and tokenizer
+model_name = "yoon-eunbin/t5-gec-model"
+tokenizer = T5Tokenizer.from_pretrained(model_name)
+model = T5ForConditionalGeneration.from_pretrained(model_name)
+
+# Set device
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+model = model.to(device)
+
+# Prepare input
+text = "He has left the room when I came into the room."
+inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=64).to(device)
+
+# Generate correction
+outputs = model.generate(**inputs, max_length=64)
+
+# Decode output
+corrected_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(f"Original: {text}")
+print(f"Corrected: {corrected_text}")