Updating to include local model

app.py

@@ -3,15 +3,15 @@ import time
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import torch
 
-#model_dir = "tinyllama_model"
-model_id = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+model_dir = "tinyllama_model"
+#model_id = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
 
-model = AutoModelForCausalLM.from_pretrained(model_id, load_in_8bit=True)
-#tokenizer = AutoTokenizer.from_pretrained(model_dir)
+model = AutoModelForCausalLM.from_pretrained(model_dir)
+tokenizer = AutoTokenizer.from_pretrained(model_dir)
 
 
 # Load the TinyLlama text generation pipeline
-pipe = pipeline("text-generation", model=model)
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 #tokenizer = AutoTokenizer.from_pretrained(model_dir)
 
 # Define the inference function