Update README.md

README.md

@@ -6,7 +6,7 @@ gated: manual
 extra_gated_heading: "Access MODUS 16-modality weights"
 extra_gated_prompt: >-
   These weights are derived from ByteDance BAGEL-7B-MoT and fine-tuned on the
-  MODUS 16-modality dataset. By requesting access you agree to use them for
+  MODUS 15-modality dataset. By requesting access you agree to use them for
   research purposes only, consistent with the upstream BAGEL license.
 extra_gated_fields:
   Name: text
@@ -20,15 +20,13 @@ tags:
 library_name: safetensors
 ---
 
-# MODUS — 16-modality stage-3 (noinstr)
+# MODUS
 
-Fine-tuned BAGEL-7B-MoT for the MODUS any-to-any demo (16 aligned modalities).
+MODUS for any-to-any generation (15 aligned modalities).
 
 **Inference config (important):**
 - modality config: `conf/modalities/instruction_16mod_stage2.yaml`
-- `use_instruction=false` — run fully instruction-free (this checkpoint was
-  trained without target/condition/system instructions).
-- weights are **bf16** (matching BAGEL's own release precision).
+- weights are **bf16**.
 
 ## Files
 - `model.safetensors` — trained weights (bf16)