gemma-3n-tiny-random

50

4.0B

—

by

yujiepan

Image Model

OTHER

4B params

New

50 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

9GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

4GB+ RAM

Training Data Analysis

🟡 Average (4.3/10)

Researched training datasets used by gemma-3n-tiny-random with quality assessment

Specialized For

general

science

multilingual

reasoning

Training Datasets (3)

🔴 2.5/10

general

science

Key Strengths

•Scale and Accessibility: At 9.5+ petabytes, Common Crawl provides unprecedented scale for training d...
•Diversity: The dataset captures billions of web pages across multiple domains and content types, ena...
•Comprehensive Coverage: Despite limitations, Common Crawl attempts to represent the broader web acro...

Considerations

•Biased Coverage: The crawling process prioritizes frequently linked domains, making content from dig...
•Large-Scale Problematic Content: Contains significant amounts of hate speech, pornography, violent c...

🟡 5/10

science

multilingual

Key Strengths

•High-Quality Content: Wikipedia articles are subject to community review, fact-checking, and citatio...
•Multilingual Coverage: Available in 300+ languages, enabling training of models that understand and ...
•Structured Knowledge: Articles follow consistent formatting with clear sections, allowing models to ...

Considerations

•Language Inequality: Low-resource language editions have significantly lower quality, fewer articles...
•Biased Coverage: Reflects biases in contributor demographics; topics related to Western culture and ...

🟡 5.5/10

science

reasoning

Key Strengths

•Scientific Authority: Peer-reviewed content from established repository
•Domain-Specific: Specialized vocabulary and concepts
•Mathematical Content: Includes complex equations and notation

Considerations

•Specialized: Primarily technical and mathematical content
•English-Heavy: Predominantly English-language papers

Explore our comprehensive training dataset analysis

View All Datasets

Code Examples

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Example usage:pythontransformers

import torch

from transformers import pipeline

model_id = "yujiepan/gemma-3n-tiny-random"
pipe = pipeline(
    task="image-text-to-text",
    model=model_id,
    device=0,
    torch_dtype=torch.bfloat16
)

# temporary patch for audio tower
from accelerate.hooks import ModelHook, add_hook_to_module

class EnsureDtype(ModelHook):
    def pre_forward(self, module, *args, **kwargs):
        args = list(args)
        args[0] = args[0].to(module.dtype)
        return super().pre_forward(module, *args, **kwargs)
add_hook_to_module(pipe.model.audio_tower, EnsureDtype())

messages = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "You are a helpful assistant."}
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
            # audio is buggy for now: bf16 x fp32
            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
            {"type": "text", "text": "Which image is cuter?"},
        ]
    },
]
result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
print(result)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.