Update README.md

how to call model

README.md

@@ -1,3 +1,49 @@
----
-license: mit
----
+---
+license: mit
+---
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from datasets import load_dataset
+import torch
+
+# Load model and tokenizer from Hugging Face Hub
+repo_id = "amelkhoadry/optimized-bert-model"
+model = AutoModelForSequenceClassification.from_pretrained(repo_id)
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+
+# Load your test dataset (replace 'your_dataset'/'test' with your actual dataset and split)
+# Example uses the 'imdb' dataset as a placeholder. Replace as needed.
+test_dataset = load_dataset("imdb", split="test")
+
+# Preprocess test data using the tokenizer
+def preprocess(example):
+    return tokenizer(
+        example["text"], 
+        truncation=True,
+        padding='max_length', 
+        max_length=128
+    )
+
+test_dataset = test_dataset.map(preprocess, batched=True)
+test_dataset.set_format(type='torch', columns=['input_ids', 'attention_mask', 'label'])
+
+# Predict on test dataset
+model.eval()
+predictions = []
+labels = []
+with torch.no_grad():
+    for batch in torch.utils.data.DataLoader(test_dataset, batch_size=32):
+        input_ids = batch["input_ids"]
+        attention_mask = batch["attention_mask"]
+        outputs = model(input_ids=input_ids, attention_mask=attention_mask)
+        logits = outputs.logits
+        preds = torch.argmax(logits, dim=1)
+        predictions.extend(preds.tolist())
+        labels.extend(batch["label"].tolist())
+
+# Example: print the first 10 predictions and labels
+print("First 10 predictions:", predictions[:10])
+print("First 10 actual labels:", labels[:10])
+
+# If you want to compute accuracy:
+accuracy = sum([int(p == l) for p, l in zip(predictions, labels)]) / len(labels)
+print(f"Test Accuracy: {accuracy:.4f}")