diff --git a/run_web_demo.sh b/run_web_demo.sh
new file mode 100755
index 0000000..f3f9a8b
--- /dev/null
+++ b/run_web_demo.sh
@@ -0,0 +1,45 @@
+#!/usr/bin/env bash
+
+cd "$(dirname "$0")"
+thisDir=$(pwd)
+
+function performInstall() {
+    set -e
+
+    pushd "$thisDir"
+    pip3 install -r requirements.txt
+    pip3 install gradio mdtex2html scipy
+
+    if [[ ! -d flash-attention ]]; then
+        if ! git clone -b v1.0.8 https://github.com/Dao-AILab/flash-attention; then
+            echo "Clone flash-attention failed, please install it manually."
+            return 0
+        fi
+    fi
+
+    cd flash-attention &&
+        pip3 install . &&
+        pip3 install csrc/layer_norm &&
+        pip3 install csrc/rotary ||
+        echo "Install flash-attention failed, please install it manually."
+    popd
+}
+
+echo "Starting WebUI..."
+
+if ! python3 web_demo.py; then
+    echo "Run demo failed, install the deps and try again? (y/n)"
+    # auto perform install if in docker
+    if [[ -t 0 ]] && [[ -t 1 ]] && [[ ! -f "/.dockerenv" ]]; then
+        read doInstall
+    else
+        doInstall="y"
+    fi
+
+    if ! [[ "$doInstall" =~ y|Y ]]; then
+        exit 1
+    fi
+
+    echo "Installing deps, and try again..."
+    performInstall && python3 web_demo.py
+fi
diff --git a/web_demo.py b/web_demo.py
new file mode 100755
index 0000000..8b37b02
--- /dev/null
+++ b/web_demo.py
@@ -0,0 +1,109 @@
+#!/usr/bin/env python3
+
+""" Ref: https://github.com/THUDM/ChatGLM2-6B/blob/main/web_demo.py """
+
+from transformers import AutoTokenizer
+import gradio as gr
+import mdtex2html
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers.generation import GenerationConfig
+import sys
+
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True).eval()
+model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True) 
+
+if len(sys.argv) > 1 and sys.argv[1] == "--exit":
+    exit(0)
+
+def postprocess(self, y):
+    if y is None:
+        return []
+    for i, (message, response) in enumerate(y):
+        y[i] = (
+            None if message is None else mdtex2html.convert((message)),
+            None if response is None else mdtex2html.convert(response),
+        )
+    return y
+
+
+gr.Chatbot.postprocess = postprocess
+
+
+def parse_text(text):
+    """copy from https://github.com/GaiZhenbiao/ChuanhuChatGPT/"""
+    lines = text.split("\n")
+    lines = [line for line in lines if line != ""]
+    count = 0
+    for i, line in enumerate(lines):
+        if "```" in line:
+            count += 1
+            items = line.split('`')
+            if count % 2 == 1:
+                lines[i] = f'<pre><code class="language-{items[-1]}">'
+            else:
+                lines[i] = f'<br></code></pre>'
+        else:
+            if i > 0:
+                if count % 2 == 1:
+                    line = line.replace("`", "\`")
+                    line = line.replace("<", "&lt;")
+                    line = line.replace(">", "&gt;")
+                    line = line.replace(" ", "&nbsp;")
+                    line = line.replace("*", "&ast;")
+                    line = line.replace("_", "&lowbar;")
+                    line = line.replace("-", "&#45;")
+                    line = line.replace(".", "&#46;")
+                    line = line.replace("!", "&#33;")
+                    line = line.replace("(", "&#40;")
+                    line = line.replace(")", "&#41;")
+                    line = line.replace("$", "&#36;")
+                lines[i] = "<br>"+line
+    text = "".join(lines)
+    return text
+
+def predict(input, chatbot, history, past_key_values):
+    print('Q: ' + parse_text(input))
+    chatbot.append((parse_text(input), ""))
+    fullResponse = "";
+
+    for response in model.chat(tokenizer, input, history=history, stream=True):
+        chatbot[-1] = (parse_text(input), parse_text(response))
+
+        yield chatbot, history, past_key_values
+        fullResponse = parse_text(response);
+    
+    print("A: " + parse_text(fullResponse))
+
+
+def reset_user_input():
+    return gr.update(value='')
+
+
+def reset_state():
+    return [], [], None
+
+
+with gr.Blocks() as demo:
+    gr.HTML("""<h1 align="center">通义千问 - QwenLM/Qwen-7B</h1>""")
+
+    chatbot = gr.Chatbot()
+    with gr.Row():
+        with gr.Column(scale=4):
+            with gr.Column(scale=12):
+                user_input = gr.Textbox(show_label=False, placeholder="Input...", lines=10).style(
+                    container=False)
+            with gr.Column(min_width=32, scale=1):
+                submitBtn = gr.Button("Submit", variant="primary")
+        with gr.Column(scale=1):
+            emptyBtn = gr.Button("Clear History")
+
+    history = gr.State([])
+    past_key_values = gr.State(None)
+
+    submitBtn.click(predict, [user_input, chatbot, history, past_key_values],
+                    [chatbot, history, past_key_values], show_progress=True)
+    submitBtn.click(reset_user_input, [], [user_input])
+    emptyBtn.click(reset_state, outputs=[chatbot, history, past_key_values], show_progress=True)
+
+demo.queue().launch(share=False, inbrowser=True, server_port=80, server_name="0.0.0.0")