Create app.py

app.py

@@ -0,0 +1,19 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from fastapi import FastAPI, Body
+
+app = FastAPI()
+
+# Load pre-trained model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B")
+
+@app.post("/generate")
+async def generate_text(input_text: str = Body(..., embed=True)):
+    input_ids = tokenizer.encode(input_text, return_tensors='pt')
+    output = model.generate(input_ids, max_length=50, num_beams=4)
+    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    return {"generated_text": generated_text}
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)