Update app.py

app.py

@@ -6,29 +6,16 @@ import gradio as gr
 import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+import sqlite3
+
+
 
 MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 DESCRIPTION = """\
-# Llama-2 13B Chat
-
-This Space demonstrates model [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) by Meta, a Llama 2 model with 13B parameters fine-tuned for chat instructions. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).
-
-🔎 For more details about the Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).
-
-🔨 Looking for an even more powerful model? Check out the large [**70B** model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
-🐇 For a smaller model that you can run on many GPUs, check our [7B model demo](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat).
-
-"""
-
-LICENSE = """
-<p/>
-
----
-As a derivate work of [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) by Meta,
-this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat/blob/main/USE_POLICY.md).
+# Llama-3 7B MRC \
 """
 
 if not torch.cuda.is_available():
@@ -42,6 +29,26 @@ if torch.cuda.is_available():
     tokenizer.use_default_system_prompt = False
 
 
+_TABLE = """
+    CREATE TABLE IF NOT EXISTS Item(
+        id INTEGER PRIMARY KEY AUTOINCREMENT,
+        question TEXT NOT NULL,
+        answer TEXT NOT NULL,
+        timestamp TIMESTAMP DEFAULT (DATETIME('now', 'localtime'))
+    );
+"""
+
+INSERT = """
+    INSERT INTO Item(question, answer) VALUES(?, ?);
+"""
+
+
+connect = sqlite3.connect(db_path, check_same_thread=False)
+cursor = self.connect.cursor()
+cursor.execute(_TABLE)
+connect.commit()
+
+
 @spaces.GPU
 def generate(
     message: str,
@@ -86,7 +93,11 @@ def generate(
         outputs.append(text)
         yield "".join(outputs)
 
+    self.cursor.execute(INSERT, (message, "".join(outputs)))
+    self.connect.commit()
+
 
+    
 chat_interface = gr.ChatInterface(
     fn=generate,
     additional_inputs=[
@@ -103,7 +114,7 @@ chat_interface = gr.ChatInterface(
             minimum=0.1,
             maximum=4.0,
             step=0.1,
-            value=0.6,
+            value=0.1,
         ),
         gr.Slider(
             label="Top-p (nucleus sampling)",
@@ -124,7 +135,7 @@ chat_interface = gr.ChatInterface(
             minimum=1.0,
             maximum=2.0,
             step=0.05,
-            value=1.2,
+            value=1.15,
         ),
     ],
     stop_btn=None,