Hugging Face's logo

chenbhao
/
omni

ONNX
Safetensors
English
omni
llm
multimodal
vlm
vam
voice
training-framework
Model card Files
xet
 Community
omni / src /trainers

Commit History

  1. feat: add VAM SFT mini training (T2A Stage 1)

    chenbhao
    7036629

  2. feat: add VLM SFT mini configs, resume training, dataset streaming, and eval fixes

    chenbhao
    9a1a7d2

  1. refactor: rename VLM configs, add VLM SFT configs, and improve model loading⁠

    chenbhao +1: Claude Opus 4.6
    56d3c4a

  2. refactor: reorganize dataset into lm/vlm/vam subdirectories⁠

    chenbhao +1: Claude Opus 4.6
    d9f29d1

  3. rename minimind→omni in model_type, eval/convert scripts, and docs

    chenbhao
    2c87b68

  4. reorganize configs into subdirs lm/vlm/vam, remove runs/, add interview docs for pretrain & full_sft

    chenbhao
    d58698c

  5. cleanup: remove deprecated doc files, update src training utils

    chenbhao
    64d62ee

  1. Add local training logger that writes to {save_dir}/{save_weight}.log

    chenbhao
    17c552f

  2. Add tokenizer training script and save trained tokenizer into checkpoint dir

    chenbhao
    1909c9c

  3. Flatten src layout: drop omni namespace, modules live directly under src/⁠

    chenbhao
    92c7321