Create app.py

app.py

@@ -0,0 +1,35 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
+
+# Define the input schema
+class ModelInput(BaseModel):
+    prompt: str
+    max_new_tokens: int = 50  # Optional: Defaults to 50 tokens
+
+# Initialize FastAPI app
+app = FastAPI()
+
+# Load your model and tokenizer
+model_path = "khurrameycon/SmolLM-135M-Instruct-qa_pairs_converted.json-25epochs"  # Update with your model directory
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(model_path)
+
+# Initialize the pipeline
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+@app.post("/generate")
+def generate_text(input: ModelInput):
+    try:
+        result = generator(
+            input.prompt,
+            max_new_tokens=input.max_new_tokens,
+            return_full_text=False,
+        )
+        return {"generated_text": result[0]["generated_text"]}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.get("/")
+def root():
+    return {"message": "Welcome to the Hugging Face Model API!"}