README.md

---
license: apache-2.0
pipeline_tag: image-text-to-text
library_name: transformers
---

# CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning

📖<a href="https://huggingface.co/papers/2509.22647">Paper</a> | 💻<a href="https://github.com/InternLM/CapRL">Code</a> | 🤗<a href="https://huggingface.co/internlm/CapRL-3B">CapRL-3B Model</a> |
  🤗<a href="https://huggingface.co/datasets/internlm/CapRL-2M">CapRL-2M Dataset</a> |🤗<a href="https://huggingface.co/collections/long-xing1/caprl-68d64ac32ded31596c36e189">CapRL Collection</a>


**CapRL-Eval-3B** is the model used for answering questions based on captions, and it is a finetuned version of Qwen2.5-VL-3B. When dealing with tasks such as ChartQA (not multiple-choice questions), it provides more stable output formatting.



## Introduction
We are excited to introduce CapRL-3B, a lightweight 3B image captioner that achieves perception capabilities comparable to Qwen2.5-VL-72B.

This is the first study of applying Reinforcement Learning with Verifiable Rewards for the
open-ended and subjective image captioning task. Unlike traditional Supervised Fine-Tuning, which
can lead to models memorizing a limited set of annotated captions, our method allows the model to
explore and generate a broader range of creative and general descriptions.
CapRL is a new training paradigm featuring a decoupled two-stage pipeline. The initial
stage uses LVLMs to generate rich and accurate captions. Subsequently, the second stage evaluates
caption quality by using a vision-only LLM to perform the QA task. We also created a specific QA
curation pipeline to ensure the quality of the questions and answers used for the second stage.

By employing CapRL training framework, initializing with the Qwen2.5-VL-3B model, and using a carefully 
filtered 75K QA dataset as the training set, we obtained a highly capable captioner, CapRL-3B.

<p align="center">
  <img src="https://huggingface.co/internlm/CapRL-Eval-3B/resolve/main/assets/teaser.png" alt="Main Results on GPT2" width="750"/>
</p>
<p align="center">
  <img src="https://huggingface.co/internlm/CapRL-Eval-3B/resolve/main/assets/performance.png" alt="Main Results on GPT2" width="750"/>
</p>

## Key Features
* **Remarkable visual understanding for Chart, Infographics and Document**: CapRL-3B achieves perception accuracy and visual information coverage comparable to Qwen2.5-VL-72B.
* **Well-organized output**: The outputs of CapRL-3B are relatively well-structured, making them clear and easy to understand.
* **Detailed description for natural images**: The outputs of CapRL-3B can perfectly cover all valid visual information while containing fewer hallucinations.

## Usage
If you want to use **CapRL-3B** for captioning, you can directly follow the exact same inference approach as in [Qwen2.5-VL-series](https://github.com/QwenLM/Qwen3-VL/tree/d2240f11656bfe404b9ba56db4e51cd09f522ff1).

We recommend using **vLLM** to speed up inference.



### Start an OpenAI API Service

Run the command below to start an OpenAI-compatible API service:

```bash
vllm serve "/PATH/CapRL-3B" \
    --trust-remote-code \
    --tensor-parallel-size=1 \
    --pipeline-parallel-size=1 \
    --gpu_memory_utilization=0.95 \
    --served-model-name=caprl \
    --port 8000 \
    --host 0.0.0.0
```

Then you can use the chat API as below: (see [OpenAI API protocol document](https://platform.openai.com/docs/guides/vision/uploading-base-64-encoded-images) for more details):
```python
import base64
from openai import OpenAI
# Set OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"
client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)
image_path = "/path/to/local/image.png"
with open(image_path, "rb") as f:
    encoded_image = base64.b64encode(f.read())
encoded_image_text = encoded_image.decode("utf-8")
base64_qwen = f"data:image;base64,{encoded_image_text}"
chat_response = client.chat.completions.create(
    model="caprl",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": base64_qwen
                    },
                },
                {"type": "text", "text": "What is the text in the illustrate?"},
            ],
        },
    ],
    temperature=1.0,
    max_tokens=max_tokens,
    top_p=1.0,
    extra_body={
        "repetition_penalty": 1.0,
        },
)
print("Chat response:", chat_response)
```



## Cases
<p align="center">
  <img src="https://huggingface.co/internlm/CapRL-Eval-3B/resolve/main/assets/comparison.png" alt="Main Results on GPT2" width="750"/>
</p>

<p align="center">
  <img src="https://huggingface.co/internlm/CapRL-Eval-3B/resolve/main/assets/info_caprl.png" alt="Main Results on GPT2" width="750"/>
</p>

<p align="center">
  <img src="https://huggingface.co/internlm/CapRL-Eval-3B/resolve/main/assets/info_caprl2.png" alt="Main Results on GPT2" width="750"/>
</p>
<p align="center">
  <img src="https://huggingface.co/internlm/CapRL-Eval-3B/resolve/main/assets/natural_caprl.png" alt="Main Results on GPT2" width="750"/>
</p>