Ming-Lite-Omni-Preview: MOE架构的多模态大模型

import os
from transformers import AutoProcessor
from modeling_bailingmm import BailingMMNativeForConditionalGeneration

# build model
model = BailingMMNativeForConditionalGeneration.from_pretrained(
    "inclusionAI/Ming-Lite-Omni",
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True
).to("cuda")

assets_path = YOUR_ASSETS_PATH

# build processor
processor = AutoProcessor.from_pretrained("inclusionAI/Ming-Lite-Omni", trust_remote_code=True)

# qa
messages = [
    {
        "role": "HUMAN",
        "content": [
            {"type": "text", "text": "请详细介绍鹦鹉的生活习性。"}
        ],
    },
]
# Output:

# 鹦鹉是一种非常聪明和社交性强的鸟类，它们的生活习性非常丰富和有趣。以下是一些关于鹦鹉生活习性的详细介绍：
# ### 1. **栖息地**
# 鹦鹉主要分布在热带和亚热带地区，包括非洲、亚洲、澳大利亚和南美洲。它们通常生活在森林、草原、沙漠和城市环境中。不同种类的鹦鹉对栖息地的要求有所不同，但大多数鹦鹉喜欢有丰富植被和水源的地方。
# ### 2. **饮食**
# 鹦鹉是杂食性动物，它们的饮食非常多样化。它们的食物包括种子、坚果、水果、蔬菜、花蜜和昆虫。鹦鹉的喙非常强壮，能够轻松地打开坚硬的果壳和坚果。一些鹦鹉还会吃泥土或沙子，以帮助消化和补充矿物质。
# ......

# image qa
messages = [
    {
        "role": "HUMAN",
        "content": [
            {"type": "image", "image": os.path.join(assets_path, "flowers.jpg")},
            {"type": "text", "text": "What kind of flower is this?"},
        ],
    },
]
# Output:

# The flowers in this image are forget-me-nots. These delicate blooms are known for their small, five-petaled flowers that come in various shades of blue, pink, and white.

cot_prompt = "SYSTEM: You are a helpful assistant. When the user asks a question, your response must include two parts: first, the reasoning process enclosed in <thinking>...</thinking> tags, then the final answer enclosed in <answer>...</answer> tags. The critical answer or key result should be placed within \\boxed{}.\n"
# And your input message should be like this:
messages = [
    {
        "role": "HUMAN",
        "content": [
            {"type": "image", "image": os.path.join(assets_path, "reasoning.png")},
            {"type": "text", "text": cot_prompt + "In the rectangle $A B C D$ pictured, $M_{1}$ is the midpoint of $D C, M_{2}$ the midpoint of $A M_{1}, M_{3}$ the midpoint of $B M_{2}$ and $M_{4}$ the midpoint of $C M_{3}$. Determine the ratio of the area of the quadrilateral $M_{1} M_{2} M_{3} M_{4}$ to the area of the rectangle $A B C D$.\nChoices:\n(A) $\frac{7}{16}$\n(B) $\frac{3}{16}$\n(C) $\frac{7}{32}$\n(D) $\frac{9}{32}$\n(E) $\frac{1}{5}$"},
        ],
    },
]
# Output:
# \<think\>\nOkay, so I have this problem about a rectangle ABCD ... (thinking process omitted) ... So, the correct answer is C.\n\</think\>\n\<answer\>\\boxed{C}\</answer\>\n\n

# video qa
messages = [
    {
        "role": "HUMAN",
        "content": [
            {"type": "video", "video": os.path.join(assets_path, "yoga.mp4")},
            {"type": "text", "text": "What is the woman doing?"},
        ],
    },
]
# Output:

# The image shows a woman performing a yoga pose on a rooftop. She's in a dynamic yoga pose, with her arms and legs extended in various positions.

# multi-turn chat
messages = [
    {
        "role": "HUMAN",
        "content": [
            {"type": "text", "text": "中国的首都是哪里？"},
        ],
    },
    {
        "role": "ASSISTANT",
        "content": [
            {"type": "text", "text": "北京"},
        ],
    },
    {
        "role": "HUMAN",
        "content": [
            {"type": "text", "text": "它的占地面积是多少？有多少常住人口？"},
        ],
    },
]
# Output:

# 北京市的总面积约为16,410.54平方公里，常住人口约为21,542,000人。

# Preparation for inference
text = processor.apply_chat_template(messages, add_generation_prompt=True)
image_inputs, video_inputs, audio_inputs = processor.process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    audios=audio_inputs,
    return_tensors="pt",
)
inputs = inputs.to(model.device)
for k in inputs.keys():
    if k == "pixel_values" or k == "pixel_values_videos" or k == "audio_feats":
        inputs[k] = inputs[k].to(dtype=torch.bfloat16)

# call generate
generated_ids = model.generate(
    **inputs,
    max_new_tokens=512,
    use_cache=False,
    eos_token_id=processor.gen_terminator,
)
generated_ids_trimmed = [
        out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
    ]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)[0]
print(output_text)

# ASR
messages = [
    {
        "role": "HUMAN",
        "content": [
            {"type": "text", "text": "Please recognize the language of this speech and transcribe it. Format: oral."},
            {"type": "audio", "audio": 'data/wavs/BAC009S0915W0292.wav'},
        ],
    },
]
outputs = model.generate(messages, max_new_tokens=512)
print(outputs)

# speech2speech
messages = [
    {
        "role": "HUMAN",
        "content": [
            {"type": "audio", "audio": 'data/wavs/BAC009S0915W0292.wav'},
        ],
    },
]
outputs = model.generate(messages, max_new_tokens=512, speaker='luna', output_audio_path='out.wav', output_audio=True)
print(outputs)