Update model card: LoRA fine-tuning now supported via HelixLinearSTE

README.md

@@ -93,7 +93,7 @@ All deltas within noise. Task performance preserved after 3.6x compression.
 ## Good to Know
 
 - **GPU and CPU supported** -- runs on any CUDA GPU or CPU.
-- **Not fine-tunable** -- compressed weights are read-only (`is_trainable = False`).
+- **Fine-tunable via LoRA** — compressed weights remain frozen, but LoRA adapters attach to each `HelixLinear` layer via `HelixLinearSTE`. See `helix-substrate` for training infrastructure.
 - **Requires `helix-substrate`** -- you need `pip install "helix-substrate[hf]"`.
 - **Embeddings stored exact** -- token, position, and patch embeddings are at full precision. Only the 218 attention + MLP linear layers are compressed.