Update README.md
Browse files
README.md
CHANGED
|
@@ -22,6 +22,8 @@ Based on the same recipe as CapRL-3B, we used InternVL3.5-8B as the policy model
|
|
| 22 |
|
| 23 |
We are working on even stronger base models and upgrading our training recipe — stay tuned!
|
| 24 |
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## Introduction
|
| 27 |
We are excited to introduce CapRL-3B, a lightweight 3B image captioner that achieves perception capabilities comparable to Qwen2.5-VL-72B.
|
|
|
|
| 22 |
|
| 23 |
We are working on even stronger base models and upgrading our training recipe — stay tuned!
|
| 24 |
|
| 25 |
+
CapRL-3B-GGUF is static quants version, and CapRL-3B-i1-GGUF is weighted/imatrix quants version. Thanks for their contribution!
|
| 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.
|