Create inference.py

inference.py

@@ -0,0 +1,21 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+class HelloWorldModel(AutoModelForCausalLM):
+    def __init__(self, config):
+        super().__init__(config)
+
+    def forward(self, input_ids, **kwargs):
+        return {"logits": input_ids}
+
+def generate_text(prompt):
+    model = HelloWorldModel.from_pretrained(".")
+    tokenizer = AutoTokenizer.from_pretrained(".")
+    
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs)
+    
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+if __name__ == "__main__":
+    prompt = "hello"
+    print(generate_text(prompt))