Create inference.py

inference.py

@@ -0,0 +1,18 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+def generate_text(prompt, max_length=100):
+    model = AutoModelForCausalLM.from_pretrained("./results")
+    tokenizer = AutoTokenizer.from_pretrained("./results")
+    
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(
+        **inputs,
+        max_length=max_length,
+        num_return_sequences=1,
+        temperature=0.7,
+        top_p=0.9,
+        do_sample=True
+    )
+    
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)