---
license: other
license_name: bagel-derived
license_link: https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT
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
  research purposes only, consistent with the upstream BAGEL license.
extra_gated_fields:
  Name: text
  Affiliation: text
  I will use these weights for research purposes only: checkbox
extra_gated_button_content: "Request access"
tags:
  - multimodal
  - any-to-any
  - modus
library_name: safetensors
---

# MODUS — 16-modality stage-3 (noinstr)

Fine-tuned BAGEL-7B-MoT for the MODUS any-to-any demo (16 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).

## Files
- `model.safetensors` — trained weights (bf16)
- `ae.safetensors` — VAE (image decode)
- `config.json` / `llm_config.json` / `vit_config.json` — architecture config
- `vocab.json` / `merges.txt` / `tokenizer_config.json` — tokenizer