魔搭社区模型速递（3.30-4.12）

from PIL import Image
from modelscope import AutoModelForCausalLM, AutoProcessor
model_path = "moonshotai/Kimi-VL-A3B-Thinking"
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)
processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
image_paths = ["./figures/demo1.png", "./figures/demo2.png"]
images = [Image.open(path) for path in image_paths]
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": image_path} for image_path in image_paths
        ] + [{"type": "text", "text": "Please infer step by step who this manuscript belongs to and what it records"}],
    },
]
text = processor.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
inputs = processor(images=images, text=text, return_tensors="pt", padding=True, truncation=True).to(model.device)
generated_ids = model.generate(**inputs, max_new_tokens=2048)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
response = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)[0]
print(response)

from modelscope import AutoProcessor, Llama4ForConditionalGeneration
import torch
model_id = "LLM-Research/Llama-4-Scout-17B-16E-Instruct"
processor = AutoProcessor.from_pretrained(model_id)
model = Llama4ForConditionalGeneration.from_pretrained(
    model_id,
    attn_implementation="flex_attention",
    device_map="auto",
    torch_dtype=torch.bfloat16,
)
url1 = "https://modelscope.oss-cn-beijing.aliyuncs.com/resource/car.jpg"
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": url1},
            {"type": "text", "text": "Can you describe the image?"},
        ]
    },
]
inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=256,
)
response = processor.batch_decode(outputs[:, inputs["input_ids"].shape[-1]:])[0]
print(response)
print(outputs[0])

pip install -U dataoceanai-dolphin

dolphin audio.wav
# Download model and specify the model path
dolphin audio.wav --model small --model_dir /data/models/dolphin/
# Specify language and region
dolphin audio.wav --model small --model_dir /data/models/dolphin/ --lang_sym "zh" --region_sym "CN"
# padding speech to 30 seconds
dolphin audio.wav --model small --model_dir /data/models/dolphin/ --lang_sym "zh" --region_sym "CN" --padding_speech true

import dolphin
waveform = dolphin.load_audio("audio.wav")
model = dolphin.load_model("small", "/data/models/dolphin", "cuda")
result = model(waveform)
# Specify language and region
result = model(waveform, lang_sym="zh", region_sym="CN")
print(result.text)