Valley2，基于电商场景的多模态大模型

!git clone https://github.com/bytedance/Valley.git
%cd Valley

from valley_eagle_chat import ValleyEagleChat
from modelscope import snapshot_download
import urllib.request
# 需要把模型文件中的config.json的eagle_vision_tower和mm_vision_tower改为本地路径
model_dir = snapshot_download("bytedance-research/Valley-Eagle-7B")
!modelscope download --model=Qwen/Qwen2-VL-7B-Instruct --local_dir=./Qwen2-VL-7B-Instruct
!modelscope download --model=AI-ModelScope/siglip-so400m-patch14-384 --local_dir=./siglip-so400m-patch14-384
model = ValleyEagleChat(
    model_path=model_dir,
    padding_side = 'left',
)
url = 'http://p16-goveng-va.ibyteimg.com/tos-maliva-i-wtmo38ne4c-us/4870400481414052507~tplv-wtmo38ne4c-jpeg.jpeg'
img = urllib.request.urlopen(url=url, timeout=5).read()
request = {
    "chat_history": [
        {'role': 'system', 'content': 'You are Valley, developed by ByteDance. Your are a helpfull Assistant.'},
        {'role': 'user', 'content': 'Describe the given image.'},
    ],
    "images": [img],
}
result = model(request)
print(f"\n>>> Assistant:\n")
print(result)
from valley_eagle_chat import ValleyEagleChat
import decord
import requests
import numpy as np
from torchvision import transforms
model = ValleyEagleChat(
    model_path=model_dir,
    padding_side = 'left',
)
url = 'https://videos.pexels.com/video-files/29641276/12753127_1920_1080_25fps.mp4'
video_file = './video.mp4'
response = requests.get(url)
if response.status_code == 200:
    with open("video.mp4", "wb") as f:
        f.write(response.content)
else:
    print("download error!")
    exit(1)
video_reader = decord.VideoReader(video_file)
decord.bridge.set_bridge("torch")
video = video_reader.get_batch(
    np.linspace(0,  len(video_reader) - 1, 8).astype(np.int_)
).byte()
print([transforms.ToPILImage()(image.permute(2, 0, 1)).convert("RGB") for image in video])
request = {
    "chat_history": [
        {'role': 'system', 'content': 'You are Valley, developed by ByteDance. Your are a helpfull Assistant.'},
        {'role': 'user', 'content': 'Describe the given video.'},
    ],
    "images": [transforms.ToPILImage()(image.permute(2, 0, 1)).convert("RGB") for image in video],
}
result = model(request)
print(f"\n>>> Assistant:\n")
print(result)