---
license: apache-2.0
base_model:
- Qwen/Qwen2.5-VL-3B-Instruct
tags:
- mm math reasoning
datasets:
- open-r1/OpenR1-Math-220k
metrics:
- accuracy
---

# TBAC-VLR1-3B

## Overview
This is a multimodal language model fine-tuned by **Tencent PCG Basic Algorithm Center**. Based on Qwen2.5-VL-3B-Instruct, TBAC-VLR1-3B-SFT undergoes SFT
training using 40k sft data filtered from OpenR1-Math-220k. TBAC-VLR1-3B then employs GRPO (Group Relative Policy Optimization) and adapts Clip-Higher from DAPO, 
achieving **state-of-the-art** results on several multimodal reasoning benchmarks among models of the same size.

## Performance
| Model                     | **Average** | **MathVista**| **MathVision** | **MathVerse** | **DynaMath**  | **LogicVista** |
| :-------------------:     | :---------: | :-----------:| :------------: | :-----------: | :-----------: | :----------:   |
| Qwen2-VL-2B               |     22.4    |      48.0    |      16.1      |      17.5     |      3.8      |     26.6       |
| InternVL2.5-2B            |     23.8    |      51.1    |      14.0      |      22.3     |      4.4      |     27.3       |
| InternVL3-2B              |     31.5    |      57.6    |      20.2      |      24.5     |      14.8     |     40.3       |
| Qwen2.5-VL-3B             |     33.6    |      61.2    |      21.9      |      31.2     |      13.2     |     40.3       |
| VLM-R1-3B-Math-0305       |     34.1    |      62.7    |      21.9      |      32.2     |      13.0     |     40.5       |
| Taichu-VLR-3B             |     34.3    |      64.9    |      23.1      |      32.1     |      12.6     |     38.7       |
| VLAA-Thinker-Qwen2.5VL-3B |     35.7    |      61.0    |      24.4      |      36.4     |      18.2     |     38.5       |
| TBAC-VLR1-3B-preview      |     36.3    |      64.8    |      25.0      |      33.2     |      17.7     |     40.8       |
| TBAC-VLR1-3B-SFT          |     35.3    |      57.0    |      27.4      |      41.1     |      15.0     |     36.1       |
| TBAC-VLR1-3B              |   **36.7**  |      57.5    |      28.7      |      41.1     |      16.1     |     40.0       | 
 
<!-- ![Performance](./assets/performance.png) -->

<!-- ![Performance](https://cdn-uploads.huggingface.co/production/uploads/669f83bf353227efaefe83d9/ZXZShbuxRBWIzEeV9-WMt.png) -->

<!-- The compared results are sourced from https://opencompass.org.cn. -->

The results of our model are self-reported, obtained by running evaluations offline on each benchmark.

## Usage
```python
from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "TencentBAC/TBAC-VLR1-3B", torch_dtype="auto", device_map="auto"
)

processor = AutoProcessor.from_pretrained("TencentBAC/TBAC-VLR1-3B")

messages = [
    {
        "role": "system",
        "content": "You FIRST think about the reasoning process as an internal monologue and then provide the final answer. The reasoning process MUST BE enclosed within <think> </think> tags. The final answer MUST BE put in \\boxed{}."
    },
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": image_path,
            },
            {"type": "text", "text": query},
        ],
    }
]

# 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, do_sample=False)
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
If you find our model useful in your research, please consider giving ❤️ and citations. Thanks!
```
@misc{Ou2025TBACVLR1,
  title = {TBAC-VLR1-3B},
  author = {Ou, Linyu and Xu, Junzhe and Yin, Yuyang},
  year = {2025},
  url = {https://huggingface.co/TencentBAC/TBAC-VLR1-3B},
}
```

---

**About**

Created by the Tencent PCG Basic Algorithm Center. All rights reserved.