Update app.py

app.py

@@ -5,15 +5,15 @@ from langchain import PromptTemplate, LLMChain
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 from huggingface_hub import login
 # API Key de Hugging Face
-api_key = "FIREWORKS"
+huggingface_token = st.secrets["FIREWORKS"]
 # Autenticar
 login(api_key)
 
 
 # Configurar modelo Llama 3.1
 model_id = "meta-llama/Llama-3.2-1B"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(model_id, tokenizer = hugginface_token)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto",token=huggingface_token, torch_dtype=torch.float16)
 
 # Crear pipeline con Fireworks
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_length=1024)