$ pip install -U transformers

from modelscope import AutoProcessor, Gemma3nForConditionalGeneration
from PIL import Image
import requests
import torch
model_id = "google/gemma-3n-e4b-it"
model = Gemma3nForConditionalGeneration.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16,).eval()
processor = AutoProcessor.from_pretrained(model_id)
messages = [
    {
        "role": "system",
        "content": [{"type": "text", "text": "You are a helpful assistant."}]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
            {"type": "text", "text": "Describe this image in detail."}
        ]
    }
]
inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)
input_len = inputs["input_ids"].shape[-1]
with torch.inference_mode():
    generation = model.generate(**inputs, max_new_tokens=100, do_sample=False)
    generation = generation[0][input_len:]
decoded = processor.decode(generation, skip_special_tokens=True)
print(decoded)
# **Overall Impression:** The image is a close-up shot of a vibrant garden scene,
# focusing on a cluster of pink cosmos flowers and a busy bumblebee.
# It has a slightly soft, natural feel, likely captured in daylight.

# pip install git+https://github.com/modelscope/ms-swift.git
git clone https://github.com/modelscope/ms-swift.git
cd ms-swift
pip install -e .

CUDA_VISIBLE_DEVICES=0 \
swift sft \
    --model google/gemma-3n-E4B-it \
    --dataset AI-ModelScope/LaTeX_OCR:human_handwrite#20000 \
    --train_type lora \
    --torch_dtype bfloat16 \
    --num_train_epochs 1 \
    --per_device_train_batch_size 1 \
    --per_device_eval_batch_size 1 \
    --learning_rate 1e-4 \
    --lora_rank 8 \
    --lora_alpha 32 \
    --target_modules all-linear \
    --freeze_vit true \
    --gradient_accumulation_steps 16 \
    --eval_steps 50 \
    --save_steps 50 \
    --save_total_limit 5 \
    --logging_steps 5 \
    --max_length 2048 \
    --output_dir output \
    --warmup_ratio 0.05 \
    --dataloader_num_workers 4

{"messages": [{"role": "user", "content": "浙江的省会在哪？"}, {"role": "assistant", "content": "浙江的省会在杭州。"}]}
{"messages": [{"role": "user", "content": "<image><image>两张图片有什么区别"}, {"role": "assistant", "content": "前一张是小猫，后一张是小狗"}], "images": ["/xxx/x.jpg", "/xxx/x.png"]}
{"messages": [{"role": "system", "content": "你是个有用无害的助手"}, {"role": "user", "content": "<audio>猜测一下演讲者的年龄和性别"}, {"role": "assistant", "content": "20岁左右的女性"}], "videos": ["/xxx/x.wav"]}

CUDA_VISIBLE_DEVICES=0 \
swift infer \
    --adapters output/vx-xxx/checkpoint-xxx \
    --stream false \
    --max_batch_size 1 \
    --load_data_args true \
    --max_new_tokens 2048

CUDA_VISIBLE_DEVICES=0 \
swift export \
    --adapters output/vx-xxx/checkpoint-xxx \
    --push_to_hub true \
    --hub_model_id '<your-model-id>' \
    --hub_token '<your-sdk-token>'