Update app.py

app.py

@@ -6,7 +6,7 @@ from threading import Thread
 import torch
 import spaces
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextIteratorStreamer
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextIteratorStreamer, AutoModelForSeq2SeqLM
 
 subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
@@ -72,7 +72,7 @@ quantization_config = BitsAndBytesConfig(
     bnb_4bit_compute_dtype=torch.bfloat16
 )
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
-model = AutoModelForCausalLM.from_pretrained(
+model = AutoModelForSeq2SeqLM.from_pretrained(
     MODEL_ID,
     device_map="auto",
     quantization_config=quantization_config,
@@ -85,12 +85,11 @@ gr.ChatInterface(
     title=EMOJI + " " + MODEL_NAME,
     description=DESCRIPTION,
     examples=[
-        ["Can you solve the equation 2x + 3 = 11 for x?"],
-        ["Write an epic poem about Ancient Rome."],
-        ["Who was the first person to walk on the Moon?"],
-        ["Use a list comprehension to create a list of squares for numbers from 1 to 10."],
-        ["Recommend some popular science fiction books."],
-        ["Can you write a short story about a time-traveling detective?"]
+        ["هل يمكنك حل المعادلة 2x + 3 = 11 للمتغير x؟"],
+        ["اكتب قصيدة ملحمية عن مدينة القدس الشريفة."],
+        ["من كان أول شخص يمشي على سطح القمر؟"],
+        ["أوصِ ببعض كتب الخيال العلمي الشهيرة."],
+        ["هل يمكنك كتابة قصة قصيرة عن محقق يسافر عبر الزمن؟"]
     ],
     additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False),
     additional_inputs=[