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

Libraries

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

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

pipe = pipeline("image-text-to-text", model="internlm/CapRL-Eval-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-Eval-3B")
model = AutoModelForImageTextToText.from_pretrained("internlm/CapRL-Eval-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

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "internlm/CapRL-Eval-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-Eval-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-Eval-3B

SGLang

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

Improve model card: Add pipeline tag, library name, code link, and update image paths

by nielsr HF Staff - opened Sep 30, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+14

-9

Files changed (1) hide show

README.md +14 -9

README.md CHANGED Viewed

@@ -1,8 +1,13 @@
 ---
 license: apache-2.0
 ---
-📖<a href="https://arxiv.org/abs/2509.22647">Paper</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> | 🤗<a href="https://huggingface.co/papers/2509.22647">Daily Paper</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.
@@ -25,10 +30,10 @@ By employing CapRL training framework, initializing with the Qwen2.5-VL-3B model
 filtered 75K QA dataset as the training set, we obtained a highly capable captioner, CapRL-3B.
 <p align="center">
-  <img src="./assets/teaser.png" alt="Main Results on GPT2" width="750"/>
 </p>
 <p align="center">
-  <img src="./assets/performance.png" alt="Main Results on GPT2" width="750"/>
 </p>
 ## Key Features
@@ -105,16 +110,16 @@ print("Chat response:", chat_response)
 ## Cases
 <p align="center">
-  <img src="./assets/comparison.png" alt="Main Results on GPT2" width="750"/>
 </p>
 <p align="center">
-  <img src="./assets/info_caprl.png" alt="Main Results on GPT2" width="750"/>
 </p>
 <p align="center">
-  <img src="./assets/info_caprl2.png" alt="Main Results on GPT2" width="750"/>
 </p>
 <p align="center">
-  <img src="./assets/natural_caprl.png" alt="Main Results on GPT2" width="750"/>
-</p>

 ---
 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.
 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
 ## 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>