MODUS β€” 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 β€” 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 β€” trained weights (bf16)
  • ae.safetensors β€” VAE (image decode)
  • config.json / llm_config.json / vit_config.json β€” architecture config
  • vocab.json / merges.txt / tokenizer_config.json β€” tokenizer
Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
15B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Spaces using mqye/modus-16mod-stage3 2