Remove inaccurate model card claims

README.md

@@ -15,14 +15,6 @@ tags:
 
 This repository contains the released LingBot-Video MoE 30B-A3B base model and
 its second-stage refiner in the component layout loaded natively by FastVideo.
-The transformer, refiner, VAE, and scheduler tensors come from
-[`robbyant/lingbot-video-moe-30b-a3b`](https://huggingface.co/robbyant/lingbot-video-moe-30b-a3b).
-The Qwen3-VL language weights are converted to FastVideo's fused text-only
-encoder layout.
-
-The current FastVideo port supports text-to-video inference. T2I, TI2V, vision
-conditioning, prompt rewriting, and automatic negative-prompt generation are
-not included in this package.
 
 ## Usage