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
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
| # MiniCPM-V2.6-WebUI.py
#!/usr/bin/env python
# encoding: utf-8
import torch
import argparse
from transformers import AutoModel, AutoTokenizer
import gradio as gr
from PIL import Image
from decord import VideoReader, cpu
import io
import os
import copy
import requests
import base64
import json
import traceback
import re
import modelscope_studio as mgr
# 解析参数
parser = argparse.ArgumentParser(description='demo')
parser.add_argument('--device', type=str, default='cuda', help='cuda or mps')
parser.add_argument('--multi-gpus', action='store_true', default=False, help='use multi-gpus')
args = parser.parse_args()
device = args.device
assert device in ['cuda', 'mps']
# 模型权重文件目录
model_path = '.'
# 加载模型和分词器
if 'int4' in model_path:
if device == 'mps':
print('Error: running int4 model with bitsandbytes on Mac is not supported right now.')
exit()
model = AutoModel.from_pretrained(model_path, local_files_only=True, trust_remote_code=True)
else:
if args.multi_gpus:
from accelerate import load_checkpoint_and_dispatch, init_empty_weights, infer_auto_device_map
with init_empty_weights():
model = AutoModel.from_pretrained(model_path, local_files_only=True, trust_remote_code=True, attn_implementation='sdpa', torch_dtype=torch.bfloat16)
device_map = infer_auto_device_map(model, max_memory={0: "10GB", 1: "10GB"},
no_split_module_classes=['SiglipVisionTransformer', 'Qwen2DecoderLayer'])
device_id = device_map["llm.model.embed_tokens"]
device_map["llm.lm_head"] = device_id # firtt and last layer should be in same device
device_map["vpm"] = device_id
device_map["resampler"] = device_id
device_id2 = device_map["llm.model.layers.26"]
device_map["llm.model.layers.8"] = device_id2
device_map["llm.model.layers.9"] = device_id2
device_map["llm.model.layers.10"] = device_id2
device_map["llm.model.layers.11"] = device_id2
device_map["llm.model.layers.12"] = device_id2
device_map["llm.model.layers.13"] = device_id2
device_map["llm.model.layers.14"] = device_id2
device_map["llm.model.layers.15"] = device_id2
device_map["llm.model.layers.16"] = device_id2
#print(device_map)
model = load_checkpoint_and_dispatch(model, model_path, local_files_only=True, dtype=torch.bfloat16, device_map=device_map)
else:
model = AutoModel.from_pretrained(model_path, local_files_only=True, trust_remote_code=True)
model = model.to(device=device)
tokenizer = AutoTokenizer.from_pretrained(model_path, local_files_only=True, trust_remote_code=True)
# 设置推理模式
model.eval()
ERROR_MSG = "Error, please retry"
model_name = 'MiniCPM-V 2.6'
MAX_NUM_FRAMES = 64
IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.tiff', '.webp'}
VIDEO_EXTENSIONS = {'.mp4', '.mkv', '.mov', '.avi', '.flv', '.wmv', '.webm', '.m4v'}
def get_file_extension(filename):
return os.path.splitext(filename)[1].lower()
def is_image(filename):
return get_file_extension(filename) in IMAGE_EXTENSIONS
def is_video(filename):
return get_file_extension(filename) in VIDEO_EXTENSIONS
form_radio = {
'choices': ['Beam Search', 'Sampling'],
#'value': 'Beam Search',
'value': 'Sampling',
'interactive': True,
'label': 'Decode Type'
}
def create_component(params, comp='Slider'):
if comp == 'Slider':
return gr.Slider(
minimum=params['minimum'],
maximum=params['maximum'],
value=params['value'],
step=params['step'],
interactive=params['interactive'],
label=params['label']
)
elif comp == 'Radio':
return gr.Radio(
choices=params['choices'],
value=params['value'],
interactive=params['interactive'],
label=params['label']
)
elif comp == 'Button':
return gr.Button(
value=params['value'],
interactive=True
)
def create_multimodal_input(upload_image_disabled=False, upload_video_disabled=False):
return mgr.MultimodalInput(upload_image_button_props={'label': 'Upload Image', 'disabled': upload_image_disabled, 'file_count': 'multiple'},
upload_video_button_props={'label': 'Upload Video', 'disabled': upload_video_disabled, 'file_count': 'single'},
submit_button_props={'label': 'Submit'})
def chat(img, msgs, ctx, params=None, vision_hidden_states=None):
try:
print('msgs:', msgs)
answer = model.chat(
image=None,
msgs=msgs,
tokenizer=tokenizer,
**params
)
res = re.sub(r'(<box>.*</box>)', '', answer)
res = res.replace('<ref>', '')
res = res.replace('</ref>', '')
res = res.replace('<box>', '')
answer = res.replace('</box>', '')
print('answer:', answer)
return 0, answer, None, None
except Exception as e:
print(e)
traceback.print_exc()
return -1, ERROR_MSG, None, None
def encode_image(image):
if not isinstance(image, Image.Image):
if hasattr(image, 'path'):
image = Image.open(image.path).convert("RGB")
else:
image = Image.open(image.file.path).convert("RGB")
# resize to max_size
max_size = 448*16
if max(image.size) > max_size:
w,h = image.size
if w > h:
new_w = max_size
new_h = int(h * max_size / w)
else:
new_h = max_size
new_w = int(w * max_size / h)
image = image.resize((new_w, new_h), resample=Image.BICUBIC)
return image
## save by BytesIO and convert to base64
#buffered = io.BytesIO()
#image.save(buffered, format="png")
#im_b64 = base64.b64encode(buffered.getvalue()).decode()
#return {"type": "image", "pairs": im_b64}
def encode_video(video):
def uniform_sample(l, n):
gap = len(l) / n
idxs = [int(i * gap + gap / 2) for i in range(n)]
return [l[i] for i in idxs]
if hasattr(video, 'path'):
vr = VideoReader(video.path, ctx=cpu(0))
else:
vr = VideoReader(video.file.path, ctx=cpu(0))
sample_fps = round(vr.get_avg_fps() / 1) # FPS
frame_idx = [i for i in range(0, len(vr), sample_fps)]
if len(frame_idx)>MAX_NUM_FRAMES:
frame_idx = uniform_sample(frame_idx, MAX_NUM_FRAMES)
video = vr.get_batch(frame_idx).asnumpy()
video = [Image.fromarray(v.astype('uint8')) for v in video]
video = [encode_image(v) for v in video]
print('video frames:', len(video))
return video
def check_mm_type(mm_file):
if hasattr(mm_file, 'path'):
path = mm_file.path
else:
path = mm_file.file.path
if is_image(path):
return "image"
if is_video(path):
return "video"
return None
def encode_mm_file(mm_file):
if check_mm_type(mm_file) == 'image':
return [encode_image(mm_file)]
if check_mm_type(mm_file) == 'video':
return encode_video(mm_file)
return None
def make_text(text):
#return {"type": "text", "pairs": text} # # For remote call
return text
def encode_message(_question):
files = _question.files
question = _question.text
pattern = r"\[mm_media\]\d+\[/mm_media\]"
matches = re.split(pattern, question)
message = []
if len(matches) != len(files) + 1:
gr.Warning("Number of Images not match the placeholder in text, please refresh the page to restart!")
assert len(matches) == len(files) + 1
text = matches[0].strip()
if text:
message.append(make_text(text))
for i in range(len(files)):
message += encode_mm_file(files[i])
text = matches[i + 1].strip()
if text:
message.append(make_text(text))
return message
def check_has_videos(_question):
images_cnt = 0
videos_cnt = 0
for file in _question.files:
if check_mm_type(file) == "image":
images_cnt += 1
else:
videos_cnt += 1
return images_cnt, videos_cnt
def count_video_frames(_context):
num_frames = 0
for message in _context:
for item in message["content"]:
#if item["type"] == "image": # For remote call
if isinstance(item, Image.Image):
num_frames += 1
return num_frames
def respond(_question, _chat_bot, _app_cfg, params_form):
_context = _app_cfg['ctx'].copy()
_context.append({'role': 'user', 'content': encode_message(_question)})
images_cnt = _app_cfg['images_cnt']
videos_cnt = _app_cfg['videos_cnt']
files_cnts = check_has_videos(_question)
if files_cnts[1] + videos_cnt > 1 or (files_cnts[1] + videos_cnt == 1 and files_cnts[0] + images_cnt > 0):
gr.Warning("Only supports single video file input right now!")
return _question, _chat_bot, _app_cfg
if params_form == 'Beam Search':
params = {
'sampling': False,
'num_beams': 3,
'repetition_penalty': 1.2,
"max_new_tokens": 2048
}
else:
params = {
'sampling': True,
'top_p': 0.8,
'top_k': 100,
'temperature': 0.7,
'repetition_penalty': 1.05,
"max_new_tokens": 2048
}
if files_cnts[1] + videos_cnt > 0:
params["max_inp_length"] = 4352 # 4096+256
params["use_image_id"] = False
params["max_slice_nums"] = 1 if count_video_frames(_context) > 16 else 2
code, _answer, _, sts = chat("", _context, None, params)
images_cnt += files_cnts[0]
videos_cnt += files_cnts[1]
_context.append({"role": "assistant", "content": [make_text(_answer)]})
_chat_bot.append((_question, _answer))
if code == 0:
_app_cfg['ctx']=_context
_app_cfg['sts']=sts
_app_cfg['images_cnt'] = images_cnt
_app_cfg['videos_cnt'] = videos_cnt
upload_image_disabled = videos_cnt > 0
upload_video_disabled = videos_cnt > 0 or images_cnt > 0
return create_multimodal_input(upload_image_disabled, upload_video_disabled), _chat_bot, _app_cfg
def fewshot_add_demonstration(_image, _user_message, _assistant_message, _chat_bot, _app_cfg):
ctx = _app_cfg["ctx"]
message_item = []
if _image is not None:
image = Image.open(_image).convert("RGB")
ctx.append({"role": "user", "content": [encode_image(image), make_text(_user_message)]})
message_item.append({"text": "[mm_media]1[/mm_media]" + _user_message, "files": [_image]})
else:
if _user_message:
ctx.append({"role": "user", "content": [make_text(_user_message)]})
message_item.append({"text": _user_message, "files": []})
else:
message_item.append(None)
if _assistant_message:
ctx.append({"role": "assistant", "content": [make_text(_assistant_message)]})
message_item.append({"text": _assistant_message, "files": []})
else:
message_item.append(None)
_chat_bot.append(message_item)
return None, "", "", _chat_bot, _app_cfg
def fewshot_respond(_image, _user_message, _chat_bot, _app_cfg, params_form):
user_message_contents = []
_context = _app_cfg["ctx"].copy()
if _image:
image = Image.open(_image).convert("RGB")
user_message_contents += [encode_image(image)]
if _user_message:
user_message_contents += [make_text(_user_message)]
if user_message_contents:
_context.append({"role": "user", "content": user_message_contents})
if params_form == 'Beam Search':
params = {
'sampling': False,
'num_beams': 3,
'repetition_penalty': 1.2,
"max_new_tokens": 2048
}
else:
params = {
'sampling': True,
'top_p': 0.8,
'top_k': 100,
'temperature': 0.7,
'repetition_penalty': 1.05,
"max_new_tokens": 2048
}
code, _answer, _, sts = chat("", _context, None, params)
_context.append({"role": "assistant", "content": [make_text(_answer)]})
if _image:
_chat_bot.append([
{"text": "[mm_media]1[/mm_media]" + _user_message, "files": [_image]},
{"text": _answer, "files": []}
])
else:
_chat_bot.append([
{"text": _user_message, "files": [_image]},
{"text": _answer, "files": []}
])
if code == 0:
_app_cfg['ctx']=_context
_app_cfg['sts']=sts
return None, '', '', _chat_bot, _app_cfg
def regenerate_button_clicked(_question, _image, _user_message, _assistant_message, _chat_bot, _app_cfg, params_form):
if len(_chat_bot) <= 1 or not _chat_bot[-1][1]:
gr.Warning('No question for regeneration.')
return '', _image, _user_message, _assistant_message, _chat_bot, _app_cfg
if _app_cfg["chat_type"] == "Chat":
images_cnt = _app_cfg['images_cnt']
videos_cnt = _app_cfg['videos_cnt']
_question = _chat_bot[-1][0]
_chat_bot = _chat_bot[:-1]
_app_cfg['ctx'] = _app_cfg['ctx'][:-2]
files_cnts = check_has_videos(_question)
images_cnt -= files_cnts[0]
videos_cnt -= files_cnts[1]
_app_cfg['images_cnt'] = images_cnt
_app_cfg['videos_cnt'] = videos_cnt
upload_image_disabled = videos_cnt > 0
upload_video_disabled = videos_cnt > 0 or images_cnt > 0
_question, _chat_bot, _app_cfg = respond(_question, _chat_bot, _app_cfg, params_form)
return _question, _image, _user_message, _assistant_message, _chat_bot, _app_cfg
else:
last_message = _chat_bot[-1][0]
last_image = None
last_user_message = ''
if last_message.text:
last_user_message = last_message.text
if last_message.files:
last_image = last_message.files[0].file.path
_chat_bot = _chat_bot[:-1]
_app_cfg['ctx'] = _app_cfg['ctx'][:-2]
_image, _user_message, _assistant_message, _chat_bot, _app_cfg = fewshot_respond(last_image, last_user_message, _chat_bot, _app_cfg, params_form)
return _question, _image, _user_message, _assistant_message, _chat_bot, _app_cfg
def flushed():
return gr.update(interactive=True)
def clear(txt_message, chat_bot, app_session):
txt_message.files.clear()
txt_message.text = ''
chat_bot = copy.deepcopy(init_conversation)
app_session['sts'] = None
app_session['ctx'] = []
app_session['images_cnt'] = 0
app_session['videos_cnt'] = 0
return create_multimodal_input(), chat_bot, app_session, None, '', ''
def select_chat_type(_tab, _app_cfg):
_app_cfg["chat_type"] = _tab
return _app_cfg
init_conversation = [
[
None,
{
# The first message of bot closes the typewriter.
"text": "You can talk to me now",
"flushing": False
}
],
]
css = """
video { height: auto !important; }
.example label { font-size: 16px;}
"""
introduction = """
## Features:
1. Chat with single image
2. Chat with multiple images
3. Chat with video
4. In-context few-shot learning
Click `How to use` tab to see examples.
"""
with gr.Blocks(css=css) as demo:
with gr.Tab(model_name):
with gr.Row():
with gr.Column(scale=1, min_width=300):
gr.Markdown(value=introduction)
params_form = create_component(form_radio, comp='Radio')
regenerate = create_component({'value': 'Regenerate'}, comp='Button')
clear_button = create_component({'value': 'Clear History'}, comp='Button')
with gr.Column(scale=3, min_width=500):
app_session = gr.State({'sts':None,'ctx':[], 'images_cnt': 0, 'videos_cnt': 0, 'chat_type': 'Chat'})
chat_bot = mgr.Chatbot(label=f"Chat with {model_name}", value=copy.deepcopy(init_conversation), height=600, flushing=False, bubble_full_width=False)
with gr.Tab("Chat") as chat_tab:
txt_message = create_multimodal_input()
chat_tab_label = gr.Textbox(value="Chat", interactive=False, visible=False)
txt_message.submit(
respond,
[txt_message, chat_bot, app_session, params_form],
[txt_message, chat_bot, app_session]
)
with gr.Tab("Few Shot") as fewshot_tab:
fewshot_tab_label = gr.Textbox(value="Few Shot", interactive=False, visible=False)
with gr.Row():
with gr.Column(scale=1):
image_input = gr.Image(type="filepath", sources=["upload"])
with gr.Column(scale=3):
user_message = gr.Textbox(label="User")
assistant_message = gr.Textbox(label="Assistant")
with gr.Row():
add_demonstration_button = gr.Button("Add Example")
generate_button = gr.Button(value="Generate", variant="primary")
add_demonstration_button.click(
fewshot_add_demonstration,
[image_input, user_message, assistant_message, chat_bot, app_session],
[image_input, user_message, assistant_message, chat_bot, app_session]
)
generate_button.click(
fewshot_respond,
[image_input, user_message, chat_bot, app_session, params_form],
[image_input, user_message, assistant_message, chat_bot, app_session]
)
chat_tab.select(
select_chat_type,
[chat_tab_label, app_session],
[app_session]
)
chat_tab.select( # do clear
clear,
[txt_message, chat_bot, app_session],
[txt_message, chat_bot, app_session, image_input, user_message, assistant_message]
)
fewshot_tab.select(
select_chat_type,
[fewshot_tab_label, app_session],
[app_session]
)
fewshot_tab.select( # do clear
clear,
[txt_message, chat_bot, app_session],
[txt_message, chat_bot, app_session, image_input, user_message, assistant_message]
)
chat_bot.flushed(
flushed,
outputs=[txt_message]
)
regenerate.click(
regenerate_button_clicked,
[txt_message, image_input, user_message, assistant_message, chat_bot, app_session, params_form],
[txt_message, image_input, user_message, assistant_message, chat_bot, app_session]
)
clear_button.click(
clear,
[txt_message, chat_bot, app_session],
[txt_message, chat_bot, app_session, image_input, user_message, assistant_message]
)
with gr.Tab("How to use"):
with gr.Column():
with gr.Row():
image_example = gr.Image(value="http://thunlp.oss-cn-qingdao.aliyuncs.com/multi_modal/never_delete/m_bear2.gif", label='1. Chat with single or multiple images', interactive=False, width=400, elem_classes="example")
example2 = gr.Image(value="http://thunlp.oss-cn-qingdao.aliyuncs.com/multi_modal/never_delete/video2.gif", label='2. Chat with video', interactive=False, width=400, elem_classes="example")
example3 = gr.Image(value="http://thunlp.oss-cn-qingdao.aliyuncs.com/multi_modal/never_delete/fshot.gif", label='3. Few shot', interactive=False, width=400, elem_classes="example")
# 启动WebUI: http://127.0.0.1:8885
demo.launch(share=False, debug=True, show_api=False, server_port=8885, server_name="0.0.0.0")
|
