Update README.md
Browse files
README.md
CHANGED
|
@@ -18,12 +18,13 @@ tags:
|
|
| 18 |
|
| 19 |
🤗<a href="https://huggingface.co/collections/long-xing1/caprl-68d64ac32ded31596c36e189">CapRL Collection</a> | 🤗<a href="https://huggingface.co/papers/2509.22647">Daily Paper</a>
|
| 20 |
|
| 21 |
-
|
| 22 |
|
| 23 |
-
|
| 24 |
|
| 25 |
-
|
| 26 |
|
|
|
|
| 27 |
|
| 28 |
## Introduction
|
| 29 |
We are excited to introduce CapRL-3B, a lightweight 3B image captioner that achieves perception capabilities comparable to Qwen2.5-VL-72B.
|
|
|
|
| 18 |
|
| 19 |
🤗<a href="https://huggingface.co/collections/long-xing1/caprl-68d64ac32ded31596c36e189">CapRL Collection</a> | 🤗<a href="https://huggingface.co/papers/2509.22647">Daily Paper</a>
|
| 20 |
|
| 21 |
+
📢 News
|
| 22 |
|
| 23 |
+
- 🚀 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. **Its performance significantly surpasses that of Qwen2.5-VL-72B**.
|
| 24 |
|
| 25 |
+
- 🚀 We are working on even stronger base models and upgrading our training recipe — stay tuned!
|
| 26 |
|
| 27 |
+
- 🚀 CapRL-3B-GGUF is static quants version, and CapRL-3B-i1-GGUF is weighted/imatrix quants version. Thanks for their contribution!
|
| 28 |
|
| 29 |
## Introduction
|
| 30 |
We are excited to introduce CapRL-3B, a lightweight 3B image captioner that achieves perception capabilities comparable to Qwen2.5-VL-72B.
|