Instructions to use internlm/CapRL-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use internlm/CapRL-3B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="internlm/CapRL-3B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("internlm/CapRL-3B")
model = AutoModelForImageTextToText.from_pretrained("internlm/CapRL-3B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use internlm/CapRL-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "internlm/CapRL-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "internlm/CapRL-3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/internlm/CapRL-3B

SGLang

How to use internlm/CapRL-3B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "internlm/CapRL-3B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "internlm/CapRL-3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "internlm/CapRL-3B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "internlm/CapRL-3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use internlm/CapRL-3B with Docker Model Runner:
```
docker model run hf.co/internlm/CapRL-3B
```

CapRL-3B / README.md

yuhangzang

Update README.md

f83373e verified about 2 months ago

preview code

raw

history blame contribute delete

8.7 kB

	---
	language:
	- en
	library_name: transformers
	license: apache-2.0
	pipeline_tag: image-text-to-text
	tags:
	- multimodal
	- image caption
	- captioning
	datasets:
	- internlm/CapRL-2M
	- internlm/CapRL-QA-75K
	---

	# CapRL
	📖<a href="https://arxiv.org/abs/2509.22647">Paper</a> \| 🏠<a href="https://github.com/InternLM/CapRL">Github</a> \| 🤗<a href="https://huggingface.co/collections/long-xing1/caprl-68d64ac32ded31596c36e189">CapRL Collection</a> \| 🤗<a href="https://huggingface.co/papers/2509.22647">Daily Paper</a>

	### CapRL Series Model & Dataset
	\| Series \| Models & Resources \|
	\| :--- \| :--- \|
	\| CapRL 2.0 Series \| [🤗 CapRL-Qwen3VL-2B](https://huggingface.co/internlm/CapRL-Qwen3VL-2B) \\| [🤗 CapRL-Qwen3VL-4B](https://huggingface.co/internlm/CapRL-Qwen3VL-4B) \\| [📦 CapRL-Qwen3VL-2B-GGUF](https://huggingface.co/internlm/CapRL-Qwen3VL-2B-GGUF) \\| [📦 CapRL-Qwen3VL-4B-GGUF](https://huggingface.co/internlm/CapRL-Qwen3VL-4B-GGUF) \\| [🌈CapRL-Qwen3VL-4B Space](https://huggingface.co/spaces/yuhangzang/CapRL-Qwen3VL-4B)
	\| CapRL 1.0 Series \| [🤗 CapRL-Qwen2.5VL-3B](https://huggingface.co/internlm/CapRL-3B) \\| [🤗 CapRL-InternVL3.5-8B](https://huggingface.co/yuhangzang/CapRL-InternVL3.5-8B) \\|[📊 CapRL-QA-75K Dataset](https://huggingface.co/datasets/internlm/CapRL-QA-75K) \\| [📊 CapRL-2M Dataset](https://huggingface.co/datasets/internlm/CapRL-2M) \\| [📦 CapRL-3B-GGUF](https://huggingface.co/mradermacher/CapRL-3B-GGUF) \\| [📦 CapRL-3B-i1-GGUF](https://huggingface.co/mradermacher/CapRL-3B-i1-GGUF) \\| [🌈CapRL-Qwen2.5VL-3B Space](https://huggingface.co/spaces/yuhangzang/caprl)

	We are excited to release the CapRL 2.0 series: CapRL-Qwen3VL-2B and CapRL-Qwen3VL-4B. These models feature fewer parameters while delivering even more powerful captioning performance.
	Notably, CapRL-Qwen3VL-2B outperforms both CapRL-Qwen2.5VL-3B and Qwen2.5VL-72B in captioning tasks.
	This leap in efficiency is driven by our upgraded training recipe, which includes a more rigorous QA data filter and a significantly more diverse image dataset. We welcome everyone to try them out!

	## CapRL-3B
	Now you can try out CapRL-3B with your own images🎨!    ➡️    [🌈CapRL Space](https://huggingface.co/spaces/yuhangzang/caprl)


	When selecting between the available CapRL models, it's essential to consider the trade-off between performance and computational cost.
	This guide will help you choose the most suitable model for your specific needs:
	\|Model\|Parameters\|Strength\|
	\|-\|-\|-\|
	\|🤗[CapRL-3B](https://huggingface.co/internlm/CapRL-3B)\|3B\|Speed, Efficiency\|
	\|🤗[CapRL-InternVL3.5-8B](https://huggingface.co/yuhangzang/CapRL-InternVL3.5-8B)\|8B\|High Performance, Advanced Captioning Ability\|

	## 📢 News
	We are working on even stronger base models and upgrading our training recipe — stay tuned!
	- 🔥 [04/16/2026] We have released the [CapRL-QA-75K](https://huggingface.co/datasets/internlm/CapRL-QA-75K) training dataset!
	- 🔥 [12/24/2025] We are excited to release the CapRL 2.0 series: [CapRL-Qwen3VL-2B](https://huggingface.co/internlm/CapRL-Qwen3VL-2B) and [CapRL-Qwen3VL-4B](https://huggingface.co/internlm/CapRL-Qwen3VL-4B)!
	- 🔥 [12/24/2025] The total downloads of the CapRL-related [models and dataset](https://huggingface.co/collections/long-xing1/caprl-68d64ac32ded31596c36e189) reached 17,000!
	- 🔥 [10/15/2025] The total downloads of the CapRL-related [models and dataset](https://huggingface.co/collections/long-xing1/caprl-68d64ac32ded31596c36e189) reached 6,000 within just 20 days!
	- 🚀 [10/15/2025] We are excited to announce the release of [CapRL-InternVL3.5-8B](https://huggingface.co/internlm/CapRL-InternVL3.5-8B), whose image captioning capability outperforms Qwen2.5-VL-72B!
	- 🚀 [10/15/2025] Thanks [mradermacher](https://huggingface.co/mradermacher) for the valuable contribution! [CapRL-3B-GGUF](https://huggingface.co/mradermacher/CapRL-3B-GGUF) is the static quants version, and [CapRL-3B-i1-GGUF](https://huggingface.co/mradermacher/CapRL-3B-i1-GGUF) is weighted/imatrix quants version.
	- 🚀 [10/15/2025] We release [QA curation code](https://github.com/InternLM/CapRL).
	- 🚀 [09/25/2025] We release CapRL repository, [CapRL-3B model](https://huggingface.co/internlm/CapRL-3B), [evaluation code](https://github.com/InternLM/CapRL) and [dataset](https://huggingface.co/datasets/internlm/CapRL-2M).

	## Introduction
	We are excited to introduce [CapRL-3B](https://huggingface.co/internlm/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 the 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](https://huggingface.co/internlm/CapRL-3B).

	<p align="center">
	<img src="./assets/teaser.png" width="750"/>
	</p>
	<p align="center">
	<img src="./assets/performance_update.png" width="750"/>
	</p>

	## Key Features
	* Remarkable visual understanding for Chart, Infographics and Document: [CapRL-3B](https://huggingface.co/internlm/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](https://huggingface.co/internlm/CapRL-3B) can perfectly cover all valid visual information while containing fewer hallucinations.

	## Usage
	If you want to use [CapRL-3B](https://huggingface.co/internlm/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="./assets/comparison.png" width="750"/>
	</p>

	<p align="center">
	<img src="./assets/info_caprl.png" width="750"/>
	</p>

	<p align="center">
	<img src="./assets/info_caprl2.png" width="750"/>
	</p>
	<p align="center">
	<img src="./assets/natural_caprl.png" width="750"/>
	</p>