Update README.md

README.md

@@ -27,9 +27,9 @@ tags:
 
 ## 📌 Introduction
 
-MOSS-VL-Base-0408 is the foundation checkpoint of the MOSS-VL series, part of the OpenMOSS ecosystem dedicated to advancing open multimodal foundation models.
+MOSS-VL-Base-0408 is the foundation checkpoint of the MOSS-VL series, part of the OpenMOSS ecosystem dedicated to advancing visual understanding.
 
-Built through four stages of multimodal pretraining only, this checkpoint serves as a high-capacity offline multimodal foundation model. It provides strong general-purpose visual-linguistic representations across image and video inputs, and is intended primarily as the base model for downstream supervised fine-tuning, alignment, and domain adaptation:
+Built through four stages of multimodal pretraining only, this checkpoint serves as a high-capacity offline multimodal foundation model. It provides strong general-purpose visual-linguistic representations across image and video inputs, and is intended primarily as the base model for downstream supervised fine-tuning, alignment, and domain adaptation
 
 1. Stage 1: Vision-language alignment
 2. Stage 2: Large-scale multimodal pretraining
@@ -42,12 +42,6 @@ Built through four stages of multimodal pretraining only, this checkpoint serves
 - 🖼️ **Strong General Multimodal Perception** — Covers single-image, multi-image, and mixed-modality offline understanding workloads.
 - 🧱 **Robust Base for Adaptation** — Serves as the pretrained backbone for future SFT, alignment, and task-specific adaptation.
 
-### 📝 Note on Variants
-
-> [!IMPORTANT]
-> **This is the base checkpoint.** It has **NOT** undergone supervised fine-tuning (SFT) or instruction tuning, and it is not the streaming variant. If you are looking for a user-facing instruction-following model, please refer to the corresponding instruct release.
-
----
 
 ## 🏗 Model Architecture