魔搭社区模型速递（3.2-3.8）

from modelscope import AutoModelForCausalLM, AutoTokenizer
model_name = "Qwen/QwQ-32B"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "How many r's are in the word \"strawberry\""
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
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]
print(response)

git clone https://github.com/tencent/HunyuanVideo-I2V
cd HunyuanVideo-I2V

pip install -r requirements.txt
pip install ninja
pip install git+https://github.com/Dao-AILab/flash-attention.git@v2.6.3

HunyuanVideo-I2V
  ├──ckpts
  │  ├──README.md
  │  ├──hunyuan-video-i2v-720p
  │  │  ├──transformers
  │  │  │  ├──mp_rank_00_model_states.pt
  ├  │  ├──vae
  ├  │  ├──lora
  │  │  │  ├──embrace_kohaya_weights.safetensors
  │  │  │  ├──hair_growth_kohaya_weights.safetensors
  │  ├──text_encoder_i2v
  │  ├──text_encoder_2
  ├──...

cd HunyuanVideo-I2V
# 下载基础模型
modelscope download --model AI-ModelScope/HunyuanVideo-I2V --local_dir ./ckpts
# 下载文本编码器MLLM
modelscope download --model AI-ModelScope/llava-llama-3-8b-v1_1-transformers --local_dir ./ckpts/text_encoder_i2v
# 下载文本编码器CLIP
modelscope download --model AI-ModelScope/clip-vit-large-patch14 --local_dir ./ckpts/text_encoder_2

cd HunyuanVideo-I2V
python3 sample_image2video.py \
    --model HYVideo-T/2 \
    --prompt "A man with short gray hair plays a red electric guitar." \
    --i2v-mode \
    --i2v-image-path ./assets/demo/i2v/imgs/0.png \
    --i2v-resolution 720p \
    --video-length 129 \
    --infer-steps 50 \
    --flow-reverse \
    --flow-shift 17.0 \
    --seed 0 \
    --use-cpu-offload \
    --save-path ./results

pip install git+https://github.com/huggingface/diffusers.git

from diffusers import CogView4Pipeline
from modelscope import snapshot_download
import torch
model_dir = snapshot_download("ZhipuAI/CogView4-6B")
pipe = CogView4Pipeline.from_pretrained(model_dir, torch_dtype=torch.bfloat16)
# Open it for reduce GPU memory usage
pipe.enable_model_cpu_offload()
pipe.vae.enable_slicing()
pipe.vae.enable_tiling()
prompt = "A vibrant cherry red sports car sits proudly under the gleaming sun, its polished exterior smooth and flawless, casting a mirror-like reflection. The car features a low, aerodynamic body, angular headlights that gaze forward like predatory eyes, and a set of black, high-gloss racing rims that contrast starkly with the red. A subtle hint of chrome embellishes the grille and exhaust, while the tinted windows suggest a luxurious and private interior. The scene conveys a sense of speed and elegance, the car appearing as if it's about to burst into a sprint along a coastal road, with the ocean's azure waves crashing in the background."
image = pipe(
    prompt=prompt,
    guidance_scale=3.5,
    num_images_per_prompt=1,
    num_inference_steps=50,
    width=1024,
    height=1024,
).images[0]
image.save("cogview4.png")

from vllm import LLM, SamplingParams
llm = LLM(model="LLM-Research/Phi-4-mini-instruct", trust_remote_code=True)
messages = [
 {"role": "system", "content": "You are a helpful AI assistant."},
 {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
 {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."},
 {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
]
sampling_params = SamplingParams(
 max_tokens=500,
 temperature=0.0,
)
output = llm.chat(messages=messages, sampling_params=sampling_params)
print(output[0].outputs[0].text)

import requests
import torch
import os
import io
from PIL import Image
import soundfile as sf
from transformers import AutoModelForCausalLM, AutoProcessor, GenerationConfig
from urllib.request import urlopen
from modelscope import snapshot_download
# Define model path
model_path = snapshot_download("LLM-Research/Phi-4-multimodal-instruct")
# Load model and processor
processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_path, 
    device_map="cuda", 
    torch_dtype="auto", 
    trust_remote_code=True, 
    #attn_implementation='flash_attention_2',
).cuda()
# Load generation config
generation_config = GenerationConfig.from_pretrained(model_path)
# Define prompt structure
user_prompt = '<|user|>'
assistant_prompt = '<|assistant|>'
prompt_suffix = '<|end|>'
# Part 1: Image Processing
print("\n--- IMAGE PROCESSING ---")
image_url = 'https://www.ilankelman.org/stopsigns/australia.jpg'
prompt = f'{user_prompt}<|image_1|>What is shown in this image?{prompt_suffix}{assistant_prompt}'
print(f'>>> Prompt\n{prompt}')
# Download and open image
image = Image.open(requests.get(image_url, stream=True).raw)
inputs = processor(text=prompt, images=image, return_tensors='pt').to('cuda:0')
# Generate response
generate_ids = model.generate(
    **inputs,
    max_new_tokens=1000,
    generation_config=generation_config,
)
generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
response = processor.batch_decode(
    generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)[0]
print(f'>>> Response\n{response}')
# Part 2: Audio Processing
print("\n--- AUDIO PROCESSING ---")
audio_url = "https://upload.wikimedia.org/wikipedia/commons/b/b0/Barbara_Sahakian_BBC_Radio4_The_Life_Scientific_29_May_2012_b01j5j24.flac"
speech_prompt = "Transcribe the audio to text, and then translate the audio to French. Use <sep> as a separator between the original transcript and the translation."
prompt = f'{user_prompt}<|audio_1|>{speech_prompt}{prompt_suffix}{assistant_prompt}'
print(f'>>> Prompt\n{prompt}')
# Downlowd and open audio file
audio, samplerate = sf.read(io.BytesIO(urlopen(audio_url).read()))
# Process with the model
inputs = processor(text=prompt, audios=[(audio, samplerate)], return_tensors='pt').to('cuda:0')
generate_ids = model.generate(
    **inputs,
    max_new_tokens=1000,
    generation_config=generation_config,
)
generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
response = processor.batch_decode(
    generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)[0]
print(f'>>> Response\n{response}')