from io import BytesIO
from urllib.request import urlopen
import librosa
from transformers import Qwen2AudioForConditionalGeneration, AutoProcessor
from modelscope import snapshot_download
import torch
model_dir = snapshot_download("Qwen/Qwen2-Audio-7B-Instruct")
processor = AutoProcessor.from_pretrained(model_dir)
model = Qwen2AudioForConditionalGeneration.from_pretrained(model_dir, device_map="auto",torch_dtype=torch.bfloat16)
conversation = [
    {"role": "user", "content": [
        {"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/guess_age_gender.wav"},
    ]},
    {"role": "assistant", "content": "Yes, the speaker is female and in her twenties."},
    {"role": "user", "content": [
        {"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/translate_to_chinese.wav"},
    ]},
]
text = processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False)
audios = []
for message in conversation:
    if isinstance(message["content"], list):
        for ele in message["content"]:
            if ele["type"] == "audio":
                audios.append(librosa.load(
                    BytesIO(urlopen(ele['audio_url']).read()), 
                    sr=processor.feature_extractor.sampling_rate)[0]
                )
inputs = processor(text=text, audios=audios, return_tensors="pt", padding=True)
inputs = inputs.to("cuda")
generate_ids = model.generate(**inputs, max_length=256)
generate_ids = generate_ids[:, inputs.input_ids.size(1):]
response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]

from modelscope import AutoModelForCausalLM, AutoTokenizer
model_name = "qwen/Qwen2-Math-72B-Instruct"
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "Find the value of $x$ that satisfies the equation $4x+5 = 6x+7$."
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

# test.py
import torch
from PIL import Image
from modelscope import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained('OpenBMB/MiniCPM-V-2_6', trust_remote_code=True,
    attn_implementation='sdpa', torch_dtype=torch.bfloat16) # sdpa or flash_attention_2, no eager
model = model.eval().cuda()
tokenizer = AutoTokenizer.from_pretrained('OpenBMB/MiniCPM-V-2_6', trust_remote_code=True)
image = Image.open('image.png').convert('RGB')
question = 'What is in the image?'
msgs = [{'role': 'user', 'content': [image, question]}]
res = model.chat(
    image=None,
    msgs=msgs,
    tokenizer=tokenizer
)
print(res)
## if you want to use streaming, please make sure sampling=True and stream=True
## the model.chat will return a generator
res = model.chat(
    image=None,
    msgs=msgs,
    tokenizer=tokenizer,
    sampling=True,
    stream=True
)
generated_text = ""
for new_text in res:
    generated_text += new_text
    print(new_text, flush=True, end='')

pip install --upgrade opencv-python transformers diffusers # Must using diffusers>=0.30.0

import torch
from diffusers import CogVideoXPipeline
from diffusers.utils import export_to_video
prompt = "A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, casting a gentle glow on the scene. The panda's face is expressive, showing concentration and joy as it plays. The background includes a small, flowing stream and vibrant green foliage, enhancing the peaceful and magical atmosphere of this unique musical performance."
pipe = CogVideoXPipeline.from_pretrained(
    "THUDM/CogVideoX-2b",
    torch_dtype=torch.float16
)
pipe.enable_model_cpu_offload()
prompt_embeds, _ = pipe.encode_prompt(
    prompt=prompt,
    do_classifier_free_guidance=True,
    num_videos_per_prompt=1,
    max_sequence_length=226,
    device="cuda",
    dtype=torch.float16,
)
video = pipe(
    num_inference_steps=50,
    guidance_scale=6,
    prompt_embeds=prompt_embeds,
).frames[0]
export_to_video(video, "output.mp4", fps=8)