Update README.md

README.md

@@ -21,7 +21,7 @@ Pre-compiled **Torq VMFB** build of LiquidAI's
 [LFM2-VL-450M](https://huggingface.co/LiquidAI/LFM2-VL-450M) vision-language model,
 ready to run on the Synaptics **SL2619** edge NPU. The SigLIP vision encoder and the
 LFM2 hybrid conv/attention text decoder both execute on the NPU in bf16; the token
-embeddings and the tied LM head run on the host CPU.
+embeddings run on the host CPU.
 
 Image + prompt → caption / visual question answering. The image is encoded once and
 its KV cache is reused, so follow-up questions about the same image stay fast.