Xinyuan VL 2B

🚀 Xinyuan-VL-2B

Xinyuan-VL-2B is a high-performance multimodal large model for the end-side from the Cylingo Group. It is fine-tuned with Qwen/Qwen2-VL-2B-Instruct and uses over 5M of multimodal data along with a small amount of plain text data. This model performs well on several authoritative benchmarks.

🚀 Quick Start

In order to rely on the thriving ecology of the open source community, we chose to fine-tune Qwen/Qwen2-VL-2B-Instruct to form our Cylingo/Xinyuan-VL-2B. Using Cylingo/Xinyuan-VL-2B is consistent with using Qwen/Qwen2-VL-2B-Instruct.

💻 Usage Examples

Basic Usage

from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# default: Load the model on the available device(s)
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "Cylingo/Xinyuan-VL-2B", torch_dtype="auto", device_map="auto"
)

# default processer
processor = AutoProcessor.from_pretrained("Cylingo/Xinyuan-VL-2B")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

# Preparation for inference
text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

📚 Documentation

We evaluated XinYuan-VL-2B using the VLMEvalKit toolkit across the following benchmarks and found that XinYuan-VL-2B outperformed Qwen/Qwen2-VL-2B-Instruct released by Alibaba Cloud, as well as other models of comparable parameter scale that have significant influence in the open-source community.

You can see the results in opencompass/open_vlm_leaderboard:

📄 License

This project is licensed under the Apache-2.0 license.