Update app.py

app.py

@@ -4,7 +4,7 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer, pipeline
 from threading import Thread
 
-model_id = "rasyosef/llama-3.2-amharic-64k-instruct-beta"
+model_id = "rasyosef/Llama-3.2-180M-Amharic-Instruct"
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id)
@@ -38,11 +38,7 @@ def generate(message, chat_history, max_new_tokens=256):
                     kwargs={
                         "text_inputs":history,
                         "max_new_tokens":max_new_tokens,
-                        "temperature":0.2,
-                        "do_sample":True,
-                        "top_k":4,
-                        "top_p":0.8,
-                        "repetition_penalty":1.25,
+                        "repetition_penalty":1.1,
                         "streamer":streamer
                         }
                     )