Update app.py

app.py

@@ -4,7 +4,7 @@ import gradio as gr
 import torch
 torch.set_num_threads(1)
 from transformers import AutoModelForCausalLM, AutoTokenizer
-from typing import Optional, Union, List, Dict, Any
+from typing import Optional, Union, List, Dict, Any, Tuple
 import random
 import time
 import datetime
@@ -31,6 +31,10 @@ from typing import List
 import numpy as np
 import tensorflow_hub as hub
 import tensorflow_text
+from dataclasses import dataclass
+
+import numpy as np
+import tensorflow as tf
 
 
 class Encoder(ABC):
@@ -52,11 +56,7 @@ class MUSEEncoder(Encoder):
         return embeds
 
 
-from dataclasses import dataclass
-from typing import Dict, List, Tuple
 
-import numpy as np
-import tensorflow as tf
 
 
 @dataclass
@@ -132,7 +132,6 @@ model = AutoModelForCausalLM.from_pretrained(
     offload_folder="./", 
     low_cpu_mem_usage=True,
 )
-model=torch.compile(model)
 tokenizer = AutoTokenizer.from_pretrained("facebook/xglm-7.5B")
 
 
@@ -294,6 +293,21 @@ with gr.Blocks(height=900) as demo:
         verbose=True, 
         memory=ConversationBufferWindowMemory(k=2),
     )
+    gr.Markdown(
+    """
+    # 🐘 WangChanGLM v0.2 demo
+
+    [Blog](https://medium.com/@iwishcognitivedissonance/wangchanglm-the-thai-turned-multilingual-instruction-following-model-7aa9a0f51f5f) | [Codes](https://github.com/pythainlp/wangchanglm) | [Demo](https://colab.research.google.com/github/pythainlp/WangChanGLM/blob/main/demo/WangChanGLM_v0_1_demo.ipynb)
+
+    ![](https://i.imgur.com/RL5Mqs3.png)
+
+
+    This demo use CPU only, so It may be slow or very slow. If you want the speed, try [Google colab](https://colab.research.google.com/github/pythainlp/WangChanGLM/blob/main/demo/WangChanGLM_v0_1_demo.ipynb).
+
+
+    **We do not guarantee a reply message.**
+    """
+    )
     with gr.Tab("Text Generation"):
         with gr.Row():
             with gr.Column():