Update chatbot.py

chatbot.py

@@ -18,6 +18,16 @@ def load_model():
     model = AutoModelForCausalLM.from_pretrained(my_model_id, device_map="auto") #,quantization_config=quantization_config
     
     return tokenizer,model
+    
+@st.cache_resource 
+def load_pipeline():
+     pipe = pipeline("text-generation", model="KvrParaskevi/Llama-2-7b-Hotel-Booking-Model", 
+        max_tokens = 50,top_k = 30, temperature = 0.1,repetition_penalty = 1.03)
+    hf = HuggingFacePipeline(pipeline=pipe)
+    return hf
+
+def generate_from_pipeline(text, pipe):
+    return pipe(text)
 
 def demo_miny_memory(model):
     # llm_data = get_Model(hugging_face_key)