Update README.md

README.md

@@ -7,6 +7,9 @@ pipeline_tag: image-text-to-text
 tags:
 - multimodal
 - image caption
+- captioning
+datasets:
+- internlm/CapRL-2M
 ---
 
 # CapRL-3B
@@ -16,21 +19,23 @@ tags:
   
   🤗<a href="https://huggingface.co/collections/long-xing1/caprl-68d64ac32ded31596c36e189">CapRL Collection</a> | 🤗<a href="https://huggingface.co/papers/2509.22647">Daily Paper</a> ｜🤗<a href="https://huggingface.co/mradermacher/CapRL-3B-GGUF">CapRL-3B-GGUF</a> ｜🤗<a href="https://huggingface.co/mradermacher/CapRL-3B-i1-GGUF">CapRL-3B-i1-GGUF</a>
 
+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)|3B|High Performance, Advanced Captioning Ability|
+
 ## 📢 News
 We are working on even stronger base models and upgrading our training recipe — stay tuned!
-- 🔥 [10/15/2025] The total downloads of the CapRL-related model and dataset reached 6,000 within just 20 days!
-- 🚀 [10/15/2025] We are excited to announce the release of **CapRL-InternVL3.5-8B**, whose image captioning capability outperforms Qwen2.5-VL-72B!
-- 🚀 [10/15/2025] We release QA curation code.
-- 🚀 [09/25/2025] We release **CapRL** repository, model, evaluation code and dataset.
-
-Based on the same recipe as CapRL-3B, we used InternVL3.5-8B as the policy model and obtained **CapRL-InternVL3.5-8B** through CapRL.
-
-
-CapRL-3B-GGUF is static quants version, and CapRL-3B-i1-GGUF is weighted/imatrix quants version. Thanks for their contribution!
-
+- 🔥 [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, a lightweight 3B image captioner that achieves perception capabilities comparable to Qwen2.5-VL-72B.
+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
@@ -41,8 +46,8 @@ stage uses LVLMs to generate rich and accurate captions. Subsequently, the secon
 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.
+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"/>
@@ -52,12 +57,12 @@ filtered 75K QA dataset as the training set, we obtained a highly capable captio
 </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.
+* **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 can perfectly cover all valid visual information while containing fewer hallucinations.
+* **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** 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).
+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.