Create app.py

app.py

@@ -0,0 +1,45 @@
+import gradio as gr
+import random
+import time
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Initialize the model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("upstage/llama-30b-instruct-2048")
+model = AutoModelForCausalLM.from_pretrained("upstage/llama-30b-instruct-2048")
+
+# Define the bot function that will generate the responses
+def bot(history):
+    user_message = history[-1][0]
+    input_ids = tokenizer.encode(user_message + tokenizer.eos_token, return_tensors='pt')
+    response = model.generate(input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+    bot_message = tokenizer.decode(response[:, input_ids.shape[-1]:][0], skip_special_tokens=True)
+    history[-1][1] = ""
+    for character in bot_message:
+        history[-1][1] += character
+        time.sleep(0.05)
+        yield history
+
+# Define the functions to add text and files to the chat history
+def add_text(history, text):
+    history = history + [(text, None)]
+    return history, gr.update(value="", interactive=False)
+
+def add_file(history, file):
+    history = history + [((file.name,), None)]
+    return history
+
+# Initialize the Gradio interface
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot([], elem_id="chatbot").style(height=750)
+    with gr.Row():
+        with gr.Column(scale=0.85):
+            txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter, or upload an image").style(container=False)
+        with gr.Column(scale=0.15, min_width=0):
+            btn = gr.UploadButton("📁", file_types=["image", "video", "audio"])
+    txt_msg = txt.submit(add_text, [chatbot, txt], [chatbot, txt], queue=False).then(bot, chatbot, chatbot)
+    txt_msg.then(lambda: gr.update(interactive=True), None, [txt], queue=False)
+    file_msg = btn.upload(add_file, [chatbot, btn], [chatbot], queue=False).then(bot, chatbot, chatbot)
+
+# Run the chatbot
+demo.queue()
+demo.launch()