魔搭社区每周速递（1.5-1.18）

!pip install vector-quantize-pytorch==1.18.5 
!pip install vocos==0.1.0
!pip install transformers==4.44.2

import torch
from PIL import Image
from modelscope import AutoModel, AutoTokenizer
# load omni model default, the default init_vision/init_audio/init_tts is True
# if load vision-only model, please set init_audio=False and init_tts=False
# if load audio-only model, please set init_vision=False
model = AutoModel.from_pretrained(
    'openbmb/MiniCPM-o-2_6',
    trust_remote_code=True,
    attn_implementation='sdpa', # sdpa or flash_attention_2
    torch_dtype=torch.bfloat16,
    init_vision=True,
    init_audio=True,
    init_tts=True
)
model = model.eval().cuda()
tokenizer = AutoTokenizer.from_pretrained('OpenBMB/MiniCPM-o-2_6', trust_remote_code=True)
# In addition to vision-only mode, tts processor and vocos also needs to be initialized
model.init_tts()
model.tts.float()
import math
import numpy as np
from PIL import Image
from moviepy.editor import VideoFileClip
import tempfile
import librosa
import soundfile as sf
def get_video_chunk_content(video_path, flatten=True):
    video = VideoFileClip(video_path)
    print('video_duration:', video.duration)
    with tempfile.NamedTemporaryFile(suffix=".wav", delete=True) as temp_audio_file:
        temp_audio_file_path = temp_audio_file.name
        video.audio.write_audiofile(temp_audio_file_path, codec="pcm_s16le", fps=16000)
        audio_np, sr = librosa.load(temp_audio_file_path, sr=16000, mono=True)
    num_units = math.ceil(video.duration)
    # 1 frame + 1s audio chunk
    contents= []
    for i in range(num_units):
        frame = video.get_frame(i+1)
        image = Image.fromarray((frame).astype(np.uint8))
        audio = audio_np[sr*i:sr*(i+1)]
        if flatten:
            contents.extend(["<unit>", image, audio])
        else:
            contents.append(["<unit>", image, audio])
    return contents
video_path="/mnt/workspace/video.mp4"
sys_msg = model.get_sys_prompt(mode='omni', language='en')
# if use voice clone prompt, please set ref_audio
# ref_audio_path = '/path/to/ref_audio'
# ref_audio, _ = librosa.load(ref_audio_path, sr=16000, mono=True)
# sys_msg = model.get_sys_prompt(ref_audio=ref_audio, mode='omni', language='en')
contents = get_video_chunk_content(video_path)
msg = {"role":"user", "content": contents}
msgs = [sys_msg, msg]
# please set generate_audio=True and output_audio_path to save the tts result
generate_audio = True
output_audio_path = '/mnt/workspace/4.wav'
res = model.chat(
    msgs=msgs,
    tokenizer=tokenizer,
    sampling=True,
    temperature=0.5,
    max_new_tokens=4096,
    omni_input=True, # please set omni_input=True when omni inference
    use_tts_template=True,
    generate_audio=generate_audio,
    output_audio_path=output_audio_path,
    max_slice_nums=1,
    use_image_id=False,
    return_dict=True
)
print(res)

import torch
from modelscope import AutoTokenizer, AutoModelForCausalLM
model_dir = "Shanghai_AI_Laboratory/internlm3-8b-instruct"
#model = AutoModelForCausalLM(model_dir, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
# Set `torch_dtype=torch.float16` to load model in float16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(model_dir, trust_remote_code=True, torch_dtype=torch.float16)
# (Optional) If on low resource devices, you can load model in 4-bit or 8-bit to further save GPU memory via bitsandbytes.
  # InternLM3 8B in 4bit will cost nearly 8GB GPU memory.
  # pip install -U bitsandbytes
  # 8-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_8bit=True)
  # 4-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_4bit=True)
model = model.eval()
model = model.cuda()
system_prompt = """You are an AI assistant whose name is InternLM (书生·浦语).
- InternLM (书生·浦语) is a conversational language model that is developed by Shanghai AI Laboratory (上海人工智能实验室). It is designed to be helpful, honest, and harmless.
- InternLM (书生·浦语) can understand and communicate fluently in the language chosen by the user such as English and 中文."""
messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Please tell me five scenic spots in Shanghai"},
 ]
tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").cuda()
generated_ids = model.generate(tokenized_chat, max_new_tokens=1024, temperature=1, repetition_penalty=1.005, top_k=40, top_p=0.8)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(tokenized_chat, generated_ids)
].cuda()
response = tokenizer.batch_decode(generated_ids)[0]
print(response)

!wget "https://modelscope.oss-cn-beijing.aliyuncs.com/resource/cloudflared-linux-amd64.deb"
!dpkg -i cloudflared-linux-amd64.deb
!git clone https://www.modelscope.cn/AI-ModelScope/ComfyUI-MajicFlus.git
%cd /mnt/workspace/ComfyUI-MajicFlus
import subprocess
import threading
import time
import socket
import urllib.request
def iframe_thread(port):
  while True:
      time.sleep(0.5)
      sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
      result = sock.connect_ex(('127.0.0.1', port))
      if result == 0:
        break
      sock.close()
  print("\nComfyUI finished loading, trying to launch cloudflared (if it gets stuck here cloudflared is having issues)\n")
  p = subprocess.Popen(["cloudflared", "tunnel", "--url", "http://127.0.0.1:{}".format(port)], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
  for line in p.stderr:
    l = line.decode()
    if "trycloudflare.com " in l:
      print("This is the URL to access ComfyUI:", l[l.find("http"):], end='')
    #print(l, end='')
threading.Thread(target=iframe_thread, daemon=True, args=(8188,)).start()
!python main.py --dont-print-server

<|im_start|>system<|im_sep|>
You are a medieval knight and must provide explanations to modern people.<|im_end|>
<|im_start|>user<|im_sep|>
How should I explain the Internet?<|im_end|>
<|im_start|>assistant<|im_sep|>

import transformers
from modelscope import snapshot_download
model_dir = snapshot_download("LLM-Research/phi-4")
pipeline = transformers.pipeline(
    "text-generation",
    model=model_dir,
    model_kwargs={"torch_dtype": "auto"},
    device_map="auto",
)
messages = [
    {"role": "system", "content": "You are a medieval knight and must provide explanations to modern people."},
    {"role": "user", "content": "How should I explain the Internet?"},
]
outputs = pipeline(messages, max_new_tokens=128)
print(outputs[0]["generated_text"][-1])

conda create -n memo python=3.10 -y
conda activate memo
conda install -c conda-forge ffmpeg -y
pip install -e .

python inference.py --config configs/inference.yaml --input_image <IMAGE_PATH> --input_audio <AUDIO_PATH> --output_dir <SAVE_PATH>

python inference.py --config configs/inference.yaml --input_image assets/examples/dicaprio.jpg --input_audio assets/examples/speech.wav --output_dir outputs

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)