Add vision demo

cli_demo_vision.py

@@ -0,0 +1,65 @@
+import os
+import platform
+import signal
+from transformers import AutoTokenizer, AutoModel
+import readline
+
+tokenizer = AutoTokenizer.from_pretrained("THUDM/visualglm-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained("THUDM/visualglm-6b", trust_remote_code=True).half().cuda()
+model = model.eval()
+
+os_name = platform.system()
+clear_command = 'cls' if os_name == 'Windows' else 'clear'
+stop_stream = False
+
+
+def build_prompt(history, prefix):
+    prompt = prefix
+    for query, response in history:
+        prompt += f"\n\n用户：{query}"
+        prompt += f"\n\nChatGLM-6B：{response}"
+    return prompt
+
+
+def signal_handler(signal, frame):
+    global stop_stream
+    stop_stream = True
+
+
+def main():
+    global stop_stream
+    while True:
+        history = []
+        prefix = "欢迎使用 VisualGLM-6B 模型，输入图片路径和内容即可进行对话，clear 清空对话历史，stop 终止程序"
+        print(prefix)
+        image_path = input("\n请输入图片路径：")
+        if image_path == "stop":
+            break
+        prefix = prefix + "\n" + image_path
+        query = "描述这张图片。"
+        while True:
+            count = 0
+            for response, history in model.stream_chat(tokenizer, image_path, query, history=history):
+                if stop_stream:
+                    stop_stream = False
+                    break
+                else:
+                    count += 1
+                    if count % 8 == 0:
+                        os.system(clear_command)
+                        print(build_prompt(history, prefix), flush=True)
+                        signal.signal(signal.SIGINT, signal_handler)
+            os.system(clear_command)
+            print(build_prompt(history, prefix), flush=True)
+            query = input("\n用户：")
+            if query.strip() == "stop":
+                break
+            if query.strip() == "clear":
+                history = []
+                os.system(clear_command)
+                print(prefix)
+                continue
+
+
+if __name__ == "__main__":
+    main()

web_demo_vision.py

@@ -0,0 +1,120 @@
+from transformers import AutoModel, AutoTokenizer
+import gradio as gr
+import mdtex2html
+
+tokenizer = AutoTokenizer.from_pretrained("THUDM/visualglm-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained("THUDM/visualglm-6b", trust_remote_code=True).half().cuda()
+model = model.eval()
+
+"""Override Chatbot.postprocess"""
+
+
+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, image_path, chatbot, max_length, top_p, temperature, history):
+    if image_path is None:
+        return [(input, "图片为空！请重新上传图片并重试。")]
+    chatbot.append((parse_text(input), ""))
+    for response, history in model.stream_chat(tokenizer, image_path, input, history, max_length=max_length, top_p=top_p,
+                                               temperature=temperature):
+        chatbot[-1] = (parse_text(input), parse_text(response))
+
+        yield chatbot, history
+
+
+def predict_new_image(image_path, chatbot, max_length, top_p, temperature):
+    input, history = "描述这张图片。", []
+    chatbot.append((parse_text(input), ""))
+    for response, history in model.stream_chat(tokenizer, image_path, input, history, max_length=max_length,
+                                               top_p=top_p,
+                                               temperature=temperature):
+        chatbot[-1] = (parse_text(input), parse_text(response))
+
+        yield chatbot, history
+
+
+def reset_user_input():
+    return gr.update(value='')
+
+
+def reset_state():
+    return None, [], []
+
+
+with gr.Blocks() as demo:
+    gr.HTML("""<h1 align="center">VisualGLM</h1>""")
+
+    image_path = gr.Image(type="filepath", label="Image Prompt", value=None)
+    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")
+            max_length = gr.Slider(0, 4096, value=2048, step=1.0, label="Maximum length", interactive=True)
+            top_p = gr.Slider(0, 1, value=0.4, step=0.01, label="Top P", interactive=True)
+            temperature = gr.Slider(0, 1, value=0.8, step=0.01, label="Temperature", interactive=True)
+
+    history = gr.State([])
+
+    submitBtn.click(predict, [user_input, image_path, chatbot, max_length, top_p, temperature, history], [chatbot, history],
+                    show_progress=True)
+
+    image_path.upload(predict_new_image, [image_path, chatbot, max_length, top_p, temperature], [chatbot, history],
+                      show_progress=True)
+    image_path.clear(reset_state, outputs=[image_path, chatbot, history], show_progress=True)
+
+    submitBtn.click(reset_user_input, [], [user_input])
+
+    emptyBtn.click(reset_state, outputs=[image_path, chatbot, history], show_progress=True)
+
+demo.queue().launch(share=False, inbrowser=True)