Update app.py

app.py

@@ -9,16 +9,11 @@ app = FastAPI()
 async def install_model():
     #hf_hub_download(repo_id="TheBloke/Mistral-7B-v0.1-GGUF", filename="mistral-7b-v0.1.Q4_K_M.gguf")
     prompt = "Once upon a time, there was a"
-    # Tokenize the prompt
+    tokenizer = AutoTokenizer.from_pretrained("./mistral-7b-v0.1.Q4_K_M.gguf")
+    model = AutoModelForCausalLM.from_pretrained("./mistral-7b-v0.1.Q4_K_M.gguf")
     inputs = tokenizer(prompt, return_tensors="pt")
-    
-    # Generate text
     output = model.generate(input_ids=inputs["input_ids"], max_length=50, num_return_sequences=3, temperature=0.7)
-    
-    # Decode the generated sequences
     generated_texts = tokenizer.batch_decode(output, skip_special_tokens=True)
-    
-    # Print the generated sequences
     for i, text in enumerate(generated_texts):
         print(f"Generated Text {i+1}: {text}")
     return generated_texts