File size: 2,364 Bytes
f6165ef 50bf79e 545d59a f6165ef | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 | ---
license: apache-2.0
---
## GitHub
https://github.com/Reallm-Labs/Infi-MMR
## Inference
Our models are established on top of the Qwen2.5-VL family. So we include a simple use case here, and refer the readers to [the standard inference procedure of Qwen2.5-VL](https://github.com/QwenLM/Qwen2.5-VL).
```python
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
# default: Load the model on the available device(s)
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
"Reallm-Labs/Infi-MMR-3B", torch_dtype="auto", device_map="auto"
)
min_pixels = 256*28*28
max_pixels = 1280*28*28
processor = AutoProcessor.from_pretrained("Reallm-Labs/Infi-MMR-3B", min_pixels=min_pixels, max_pixels=max_pixels)
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(model.device)
# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=4096)
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)
```
## Citation Information
If you find this work useful, we would be grateful if you consider citing the following papers:
```bibtex
@article{liu2025infimmr,
title={Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models},
author={Zeyu Liu and Yuhang Liu and Guanghao Zhu and Congkai Xie and Zhen Li and Jianbo Yuan and Xinyao Wang and Qing Li and Shing-Chi Cheung and Shengyu Zhang and Fei Wu and Hongxia Yang},
journal={arXiv preprint arXiv:2505.23091},
year={2025}
}
``` |