Update app.py

app.py

@@ -4,6 +4,19 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer, pipeline
 from threading import Thread
 
+model_id = "rasyosef/llama-3.2-amharic-64k-instruct-beta"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+llama_am = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    pad_token_id=tokenizer.pad_token_id,
+    eos_token_id=tokenizer.eos_token_id
+  )
+
 # Function that accepts a prompt and generates text using the phi2 pipeline
 def generate(message, chat_history, max_new_tokens=256):