Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,51 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_117_IMG_8176.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_127_1E703639-9169-4EB4-8A5D-3B1E226F639B.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_14_IMG_20220721_150241.jpg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_153_IMG_20240411_102841.jpg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_155_IMG_20240403_094547.jpg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_158_IMG_20240416_141427.jpg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_159_IMG_20240416_140243.jpg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_187_mmexport1713446177339.jpg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_19_IMG_0395.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_217_IMG_3854.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_22_IMG_20240404_135935.jpg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_236_IMG_4742.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_34_IMG_0400.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_40_IMG_20170613_190017.jpg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_61_mmexport1550554859117.jpg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_64_IMG_20240409_181047.jpg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_68_IMG_0971.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_70_IMG_0581.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_72_IMG_0618.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_80_IMG_6323.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_87_IMG_5316.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14456664_88_wx_camera_1712730236546.jpg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_108_IMG_6205.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_109_IMG_5997.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_112_IMG_3570.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_117_IMG_1362.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_122_53D0E884-E012-4FFA-8BD7-8F5666A53123.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_144_IMG_8800.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_14_IMG_3852.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_162_IMG_0356.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_168_D4D36C59-2D68-4354-B05C-B3065F6581AA.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_174_IMG_8019.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_183_IMG_20240502_122921.jpg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_209_IMG_3105.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_211_IMG_9139.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_237_IMG_5909.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_257_79874AA6-4F23-4AD6-96E2-7F64039A81C0.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_261_0E3192C7-1B0D-4C4D-9788-5E7A5E6E92BA.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_262_75B3AEDF-C705-400B-AE86-3FA7A92B624C.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_265_1C4A3265-A18E-46C2-A264-4384B85A49C0.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_44_930F3702-FC28-498F-A5A7-9E01AA5AEA15.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_55_IMG_8533.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_65_IMG_20240424_121225.jpg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_75_IMG_8637.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_79_IMG_2612.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_80_IMG_2613.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/food/14521898_82_IMG_9847.jpeg filter=lfs diff=lfs merge=lfs -text
+outputs/uploaded/4.jpg filter=lfs diff=lfs merge=lfs -text

demo.py

@@ -0,0 +1,119 @@
+import os
+import random
+import numpy as np
+import torch
+import torch.backends.cudnn as cudnn
+import gradio as gr
+
+from utils import load_json, init_logger
+from demo import ConversationalAgent, CustomTheme
+
+FOOD_EXAMPLES = "demo/food_for_demo.json"
+# MODEL_PATH = "/root/share/new_models/OpenGVLab/InternVL2-2B"
+MODEL_PATH = "/root/xtuner/work_dirs/internvl_v2_internlm2_2b_lora_finetune_food/lr35_ep10"
+OUTPUT_PATH = "./outputs"
+
+def setup_seeds():
+    seed = 42
+
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+
+    cudnn.benchmark = False
+    cudnn.deterministic = True
+
+
+def main():
+    setup_seeds()
+    # logging
+    init_logger(OUTPUT_PATH)
+    # food examples
+    food_examples = load_json(FOOD_EXAMPLES)
+    
+    agent = ConversationalAgent(model_path=MODEL_PATH,
+                                outputs_dir=OUTPUT_PATH)
+    
+    theme = CustomTheme()
+    
+    titles = [
+        """<center><B><font face="Comic Sans MS" size=10>书生大模型实战营</font></B></center>"""  ## Kalam:wght@700
+        """<center><B><font face="Courier" size=5>「进阶岛」InternVL 多模态模型部署微调实践</font></B></center>"""
+    ]
+    
+    language = """Language: 中文 and English"""
+    with gr.Blocks(theme) as demo_chatbot:
+        for title in titles:
+            gr.Markdown(title)
+        # gr.Markdown(article)
+        gr.Markdown(language)
+        
+        with gr.Row():
+            with gr.Column(scale=3):
+                start_btn = gr.Button("Start Chat", variant="primary", interactive=True)
+                clear_btn = gr.Button("Clear Context", interactive=False)
+                image = gr.Image(type="pil", interactive=False)
+                upload_btn = gr.Button("🖼️ Upload Image", interactive=False)
+                
+                with gr.Accordion("Generation Settings"):                    
+                    top_p = gr.Slider(minimum=0, maximum=1, step=0.1,
+                                      value=0.8,
+                                      interactive=True,
+                                      label='top-p value',
+                                      visible=True)
+                    
+                    temperature = gr.Slider(minimum=0, maximum=1.5, step=0.1,
+                                            value=0.8,
+                                            interactive=True,
+                                            label='temperature',
+                                            visible=True)
+                    
+            with gr.Column(scale=7):
+                chat_state = gr.State()
+                chatbot = gr.Chatbot(label='InternVL2', height=800, avatar_images=((os.path.join(os.path.dirname(__file__), 'demo/user.png')), (os.path.join(os.path.dirname(__file__), "demo/bot.png"))))
+                text_input = gr.Textbox(label='User', placeholder="Please click the <Start Chat> button to start chat!", interactive=False)
+                gr.Markdown("### 输入示例")
+                def on_text_change(text):
+                    return gr.update(interactive=True)
+                text_input.change(fn=on_text_change, inputs=text_input, outputs=text_input)
+                gr.Examples(
+                    examples=[["图片中的食物通常属于哪个菜系?"],
+                              ["如果让你简单形容一下品尝图片中的食物的滋味，你会描述它"],
+                              ["去哪个地方游玩时应该品尝当地的特色美食图片中的食物?"],
+                              ["食用图片中的食物时，一般它上菜或摆盘时的特点是?"]],
+                    inputs=[text_input]
+                )
+        
+        with gr.Row():
+            gr.Markdown("### 食物快捷栏")
+        with gr.Row():
+            example_xinjiang_food = gr.Examples(examples=food_examples["新疆菜"], inputs=image, label="新疆菜")
+            example_sichuan_food = gr.Examples(examples=food_examples["川菜（四川，重庆）"], inputs=image, label="川菜（四川，重庆）")
+            example_xibei_food = gr.Examples(examples=food_examples["西北菜 （陕西，甘肃等地）"], inputs=image, label="西北菜 （陕西，甘肃等地）")
+        with gr.Row():
+            example_guizhou_food = gr.Examples(examples=food_examples["黔菜 (贵州）"], inputs=image, label="黔菜 (贵州）")
+            example_jiangsu_food = gr.Examples(examples=food_examples["苏菜（江苏）"], inputs=image, label="苏菜（江苏）")
+            example_guangdong_food = gr.Examples(examples=food_examples["粤菜（广东等地）"], inputs=image, label="粤菜（广东等地）")
+        with gr.Row():
+            example_hunan_food = gr.Examples(examples=food_examples["湘菜（湖南）"], inputs=image, label="湘菜（湖南）")
+            example_fujian_food = gr.Examples(examples=food_examples["闽菜（福建）"], inputs=image, label="闽菜（福建）")
+            example_zhejiang_food = gr.Examples(examples=food_examples["浙菜（浙江）"], inputs=image, label="浙菜（浙江）")
+        with gr.Row():
+            example_dongbei_food = gr.Examples(examples=food_examples["东北菜 （黑龙江等地）"], inputs=image, label="东北菜 （黑龙江等地）")
+            
+                
+        start_btn.click(agent.start_chat, [chat_state], [text_input, start_btn, clear_btn, image, upload_btn, chat_state])
+        clear_btn.click(agent.restart_chat, [chat_state], [chatbot, text_input, start_btn, clear_btn, image, upload_btn, chat_state], queue=False)
+        upload_btn.click(agent.upload_image, [image, chatbot, chat_state], [image, chatbot, chat_state])
+        text_input.submit(
+            agent.respond,
+            inputs=[text_input, image, chatbot, top_p, temperature, chat_state], 
+            outputs=[text_input, image, chatbot, chat_state]
+        )
+
+    demo_chatbot.launch(share=True, server_name="127.0.0.1", server_port=1096, allowed_paths=['./'])
+    demo_chatbot.queue()
+    
+
+if __name__ == "__main__":
+    main()

demo/__init__.py

@@ -0,0 +1,8 @@
+from demo.agent import ConversationalAgent
+from demo.theme import CustomTheme
+
+
+__all__ = [
+    "ConversationalAgent",
+    "CustomTheme",
+]

demo/agent.py

@@ -0,0 +1,105 @@
+import os
+import logging
+from datetime import datetime
+
+import gradio as gr
+from PIL import Image
+
+from lmdeploy import pipeline, TurbomindEngineConfig, GenerationConfig, ChatTemplateConfig
+from lmdeploy.vl import load_image
+
+class ConversationalAgent:
+    def __init__(self, 
+                 model_path,
+                 outputs_dir) -> None:
+        self.pipe = pipeline(model_path,
+                        chat_template_config=ChatTemplateConfig(model_name='internvl2-internlm2'),
+                        backend_config=TurbomindEngineConfig(session_len=8192))
+        self.uploaded_images_storage = os.path.join(outputs_dir, "uploaded")
+        self.uploaded_images_storage = os.path.abspath(self.uploaded_images_storage)
+        os.makedirs(self.uploaded_images_storage, exist_ok=True)
+        self.sess = None
+        
+    def start_chat(self, chat_state):
+        self.sess = None
+        self.context = ""
+        self.current_image_id = -1
+        self.image_list = []
+        self.pixel_values_list = []
+        self.seen_image_idx = []
+        logging.info("=" * 30 + "Start Chat" + "=" * 30)
+        
+        return (
+            #gr.update(interactive=False),  # [image] Image
+            gr.update(interactive=True, placeholder='input the text.'),  # [input_text] Textbox
+            gr.update(interactive=False),  # [start_btn] Button
+            gr.update(interactive=True),  # [clear_btn] Button
+            gr.update(interactive=True),  # [image] Image
+            gr.update(interactive=True),  # [upload_btn] Button
+            chat_state  # [chat_state] State
+        )
+        
+    def restart_chat(self, chat_state):
+        self.sess = None
+        self.context = ""
+        self.current_image_id = -1
+        self.image_list = []
+        self.pixel_values_list = []
+        self.seen_image_idx = []
+        
+        logging.info("=" * 30 + "End Chat" + "=" * 30)
+        
+        return (
+            None,  # [chatbot] Chatbot
+            #gr.update(value=None, interactive=True),  # [image] Image
+            gr.update(interactive=False, placeholder="Please click the <Start Chat> button to start chat!"),  # [input_text] Textbox
+            gr.update(interactive=True),  # [start] Button
+            gr.update(interactive=False),  # [clear] Button
+            gr.update(value=None, interactive=False),  # [image] Image
+            gr.update(interactive=False),  # [upload_btn] Button
+            chat_state  # [chat_state] State
+        )
+        
+    def upload_image(self, image: Image.Image, chat_history: gr.Chatbot, chat_state: gr.State):
+        logging.info(f"type(image): {type(image)}")
+        
+        self.image_list.append(image)        
+        save_image_path = os.path.join(self.uploaded_images_storage, "{}.jpg".format(len(os.listdir(self.uploaded_images_storage))))
+        image.save(save_image_path)
+        logging.info(f"image save path: {save_image_path}")
+        chat_history.append((gr.HTML(f'<img src="./file={save_image_path}" style="width: 200px; height: auto; display: inline-block;">'), "Received."))
+        
+        return None, chat_history, chat_state
+    
+    def respond(
+        self,
+        message,
+        image,
+        chat_history: gr.Chatbot,
+        top_p,
+        temperature,
+        chat_state,
+    ):
+        current_time = datetime.now().strftime("%b%d-%H:%M:%S")
+        logging.info(f"Time: {current_time}")
+        logging.info(f"User: {message}")
+        gen_config = GenerationConfig(top_p=top_p, temperature=temperature)
+        chat_input = message
+        if image is not None:
+            save_image_path = os.path.join(self.uploaded_images_storage, "{}.jpg".format(len(os.listdir(self.uploaded_images_storage))))
+            image.save(save_image_path)
+            logging.info(f"image save path: {save_image_path}")
+            chat_input = (message, image)
+        if self.sess is None:
+            self.sess = self.pipe.chat(chat_input, gen_config=gen_config)
+        else:
+            self.sess = self.pipe.chat(chat_input, session=self.sess, gen_config=gen_config)
+        response = self.sess.response.text
+        if image is not None:
+            chat_history.append((gr.HTML(f'{message}\n\n<img src="./file={save_image_path}" style="width: 200px; height: auto; display: inline-block;">'), response))
+        else:
+            chat_history.append((message, response))
+        
+        logging.info(f"generated text = \n{response}")        
+        
+        return "", None, chat_history, chat_state