Update app.py

app.py

@@ -6,15 +6,15 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStream
 import gradio as gr
 from threading import Thread
 
-MODEL_LIST = ["mistralai/Mistral-Nemo-Instruct-2407"]
+MODEL_LIST = ["LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct"]
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
 MODEL = os.environ.get("MODEL_ID")
 
-TITLE = "<h1><center>Mistral-Nemo</center></h1>"
+TITLE = "<h1><center>EXAONE-3.0-7.8B-Instruct</center></h1>"
 
 PLACEHOLDER = """
 <center>
-<p>The Mistral-Nemo is a pretrained generative text model of 12B parameters trained jointly by Mistral AI and NVIDIA.</p>
+<p>EXAONE-3.0-7.8B-Instruct is a pre-trained and instruction-tuned bilingual (English and Korean) generative model with 7.8 billion parameters</p>
 </center>
 """
 
@@ -75,7 +75,8 @@ def stream_chat(
         top_k = top_k,
         temperature = temperature,
         streamer=streamer,
-        pad_token_id = 10,
+        pad_token_id = 0,
+        eos_token_id = tokenizer.eos_token_id # 361
     )
 
     with torch.no_grad():
@@ -109,7 +110,7 @@ with gr.Blocks(css=CSS, theme="soft") as demo:
             ),
             gr.Slider(
                 minimum=128,
-                maximum=8192,
+                maximum=4096,
                 step=1,
                 value=1024,
                 label="Max new tokens",