Hugging Face's logo

ModerRAS
/
AniFileBERT

Token Classification
Transformers
ONNX
Safetensors
English
Japanese
Chinese
bert
anime
filename-parsing
Eval Results (legacy)
Model card Files
xet
 Community
AniFileBERT / tools

Commit History

  1. Add local training status helper

    ModerRAS
    0df0bf9

  2. Add Rust cached synthetic training runner

    ModerRAS
    a61b883

  3. Diversify synthetic path episode leaves

    ModerRAS
    4fd98b7

  4. Balance synthetic movie and special path bases

    ModerRAS
    69c4496

  5. Add Rust schema v2 synthetic augmentation

    ModerRAS
    d87ba32

  1. Fix Rust encoded cache label repairs

    ModerRAS
    7934324

  2. Add Rust encoded dataset cache

    ModerRAS
    c705a32

  3. Implement schema v2 anime filename labels

    ModerRAS
    ed49faa

  1. Document and tighten DMHY template labels

    ModerRAS
    d92b315

  1. Tighten DMHY template label heuristics

    ModerRAS
    f484458

  2. Refine high-frequency DMHY labels

    ModerRAS
    b7152ef

  3. Refine DMHY bonus labeling cases

    ModerRAS
    acafd67

  4. Improve DMHY low-frequency metadata handling

    ModerRAS
    299b1af

  5. Tighten DMHY low-frequency special cases

    ModerRAS
    f9e69dd

  6. Refine low-frequency DMHY labeling rules

    ModerRAS
    aa41de9

  7. Improve DMHY template labeling pipeline

    ModerRAS
    59042eb

  8. Verify low-frequency DMHY generated output

    ModerRAS
    93f322e

  9. Add low-frequency DMHY audit gate

    ModerRAS
    494b24c

  10. Refine DMHY template labeling rules

    ModerRAS
    79b4d87

  11. Add Rust DMHY template clustering

    ModerRAS
    736c211

  12. Add Rust DMHY template recipe applier

    ModerRAS
    7f87a1d

  1. Add DMHY prefix graph annotation workflow

    ModerRAS
    33bb11c

  2. Export DMHY metadata list

    ModerRAS
    4248c69

  3. Add DMHY digit-dedup list export

    ModerRAS
    beb7665

  4. Update relabel artifacts and pathfix export

    ModerRAS
    5af16a8

  1. Add robust LLM relabel pipeline and enforce contiguous title

    ModerRAS
    fed9d99

  2. set gpt-5.4-mini default token pricing

    ModerRAS
    8165cc3

  3. feat: add concurrency and token/cost telemetry for llm relabel runs

    ModerRAS
    7c5b41e

  4. feat: add tool-call based llm relabel pipeline and update dataset pointer

    ModerRAS
    e964ae5

  5. chore: checkpoint current training and manual relabel progress

    ModerRAS
    efb213a

  1. Add tests for combo generator

    ModerRAS
    1bef818

  2. Add balanced focus dataset generator

    ModerRAS
    651ad49

  3. Add path-aware focus dataset support

    ModerRAS
    1e1bc1f

  1. Train virtual-shard anime parser

    ModerRAS
    359ff82

  1. Organize parser modules and tools

    ModerRAS
    8c50d16