1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250
|
"""A simple web interactive chat demo based on gradio."""
from argparse import ArgumentParser from pathlib import Path
import copy import gradio as gr import os import re import secrets import tempfile
DEFAULT_CKPT_PATH = 'Qwen/Qwen-VL-Chat' BOX_TAG_PATTERN = r"<box>([\s\S]*?)</box>" PUNCTUATION = "!?。"#$%&'()*+,-/:;<=>@[\]^_`{|}~⦅⦆「」、、〃》「」『』【】〔〕〖〗〘〙〚〛〜〝〞〟〰〾〿–—‘’‛“”„‟…‧﹏."
import os os.environ['CUDA_VISIBLE_DEVICES'] = '0' from modelscope import ( snapshot_download, AutoModelForCausalLM, AutoTokenizer, GenerationConfig, ) from transformers import BitsAndBytesConfig import torch model_id = 'qwen/Qwen-VL-Chat' revision = 'v1.1.0'
model_dir = snapshot_download(model_id, revision=revision) torch.manual_seed(1234)
def _get_args(): parser = ArgumentParser() parser.add_argument("-c", "--checkpoint-path", type=str, default=DEFAULT_CKPT_PATH, help="Checkpoint name or path, default to %(default)r") parser.add_argument("--cpu-only", action="store_true", help="Run demo with CPU only")
parser.add_argument("--share", action="store_true", default=False, help="Create a publicly shareable link for the interface.") parser.add_argument("--inbrowser", action="store_true", default=False, help="Automatically launch the interface in a new tab on the default browser.") parser.add_argument("--server-port", type=int, default=8000, help="Demo server port.") parser.add_argument("--server-name", type=str, default="0.0.0.0", help="Demo server name.")
args = parser.parse_args() return args
def _load_model_tokenizer(args): tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
quantization_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.float16, bnb_4bit_quant_type='nf4', bnb_4bit_use_double_quant=True, llm_int8_skip_modules=['lm_head', 'attn_pool.attn'])
model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, offload_folder="offload_folder",fp16=True, quantization_config=quantization_config).eval() model.generation_config = GenerationConfig.from_pretrained(model_dir, trust_remote_code=True) return model, tokenizer
def _parse_text(text): 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("`", r"\`") line = line.replace("<", "<") line = line.replace(">", ">") line = line.replace(" ", " ") line = line.replace("*", "*") line = line.replace("_", "_") line = line.replace("-", "-") line = line.replace(".", ".") line = line.replace("!", "!") line = line.replace("(", "(") line = line.replace(")", ")") line = line.replace("$", "$") lines[i] = "<br>" + line text = "".join(lines) return text
def _launch_demo(args, model, tokenizer): uploaded_file_dir = os.environ.get("GRADIO_TEMP_DIR") or str( Path(tempfile.gettempdir()) / "gradio" )
def predict(_chatbot, task_history): chat_query = _chatbot[-1][0] query = task_history[-1][0] print("User: " + _parse_text(query)) history_cp = copy.deepcopy(task_history) full_response = ""
history_filter = [] pic_idx = 1 pre = "" for i, (q, a) in enumerate(history_cp): if isinstance(q, (tuple, list)): q = f'Picture {pic_idx}: <img>{q[0]}</img>' pre += q + '\n' pic_idx += 1 else: pre += q history_filter.append((pre, a)) pre = "" history, message = history_filter[:-1], history_filter[-1][0] response, history = model.chat(tokenizer, message, history=history) image = tokenizer.draw_bbox_on_latest_picture(response, history) if image is not None: temp_dir = secrets.token_hex(20) temp_dir = Path(uploaded_file_dir) / temp_dir temp_dir.mkdir(exist_ok=True, parents=True) name = f"tmp{secrets.token_hex(5)}.jpg" filename = temp_dir / name image.save(str(filename)) _chatbot[-1] = (_parse_text(chat_query), (str(filename),)) chat_response = response.replace("<ref>", "") chat_response = chat_response.replace(r"</ref>", "") chat_response = re.sub(BOX_TAG_PATTERN, "", chat_response) if chat_response != "": _chatbot.append((None, chat_response)) else: _chatbot[-1] = (_parse_text(chat_query), response) full_response = _parse_text(response)
task_history[-1] = (query, full_response) print("Qwen-VL-Chat: " + _parse_text(full_response)) return _chatbot
def regenerate(_chatbot, task_history): if not task_history: return _chatbot item = task_history[-1] if item[1] is None: return _chatbot task_history[-1] = (item[0], None) chatbot_item = _chatbot.pop(-1) if chatbot_item[0] is None: _chatbot[-1] = (_chatbot[-1][0], None) else: _chatbot.append((chatbot_item[0], None)) return predict(_chatbot, task_history)
def add_text(history, task_history, text): task_text = text if len(text) >= 2 and text[-1] in PUNCTUATION and text[-2] not in PUNCTUATION: task_text = text[:-1] history = history + [(_parse_text(text), None)] task_history = task_history + [(task_text, None)] return history, task_history, ""
def add_file(history, task_history, file): history = history + [((file.name,), None)] task_history = task_history + [((file.name,), None)] return history, task_history
def reset_user_input(): return gr.update(value="")
def reset_state(task_history): task_history.clear() return []
with gr.Blocks() as demo:
gr.Markdown("""<center><font size=8>Qwen-VL-Chat Bot</center>""") gr.Markdown( """\ <center><font size=3>This WebUI is based on Qwen-VL-Chat, developed by Alibaba Cloud. \ (本WebUI基于Qwen-VL-Chat打造,实现聊天机器人功能。)</center>""")
chatbot = gr.Chatbot(label='Qwen-VL-Chat', elem_classes="control-height", height=750) query = gr.Textbox(lines=2, label='Input') task_history = gr.State([])
with gr.Row(): empty_bin = gr.Button("🧹 Clear History (清除历史)") submit_btn = gr.Button("🚀 Submit (发送)") regen_btn = gr.Button("🤔️ Regenerate (重试)") addfile_btn = gr.UploadButton("📁 Upload (上传文件)", file_types=["image"])
submit_btn.click(add_text, [chatbot, task_history, query], [chatbot, task_history]).then( predict, [chatbot, task_history], [chatbot], show_progress=True ) submit_btn.click(reset_user_input, [], [query]) empty_bin.click(reset_state, [task_history], [chatbot], show_progress=True) regen_btn.click(regenerate, [chatbot, task_history], [chatbot], show_progress=True) addfile_btn.upload(add_file, [chatbot, task_history, addfile_btn], [chatbot, task_history], show_progress=True)
gr.Markdown("""\ <font size=2>Note: This demo is governed by the original license of Qwen-VL. \ We strongly advise users not to knowingly generate or allow others to knowingly generate harmful content, \ including hate speech, violence, pornography, deception, etc. \ (注:本演示受Qwen-VL的许可协议限制。我们强烈建议,用户不应传播及不应允许他人传播以下内容,\ 包括但不限于仇恨言论、暴力、色情、欺诈相关的有害信息。)""")
demo.queue().launch( share=args.share, inbrowser=args.inbrowser, server_port=args.server_port, server_name=args.server_name, )
def main(): args = _get_args()
model, tokenizer = _load_model_tokenizer(args)
_launch_demo(args, model, tokenizer)
if __name__ == '__main__': main()
|