Hugging Face's logo

emrevrg
/
AUBIN-12B

PEFT
Safetensors
decision-model
typed-decisions
calibrated
lora
aubin
norovox
open-weights
Model card Files
xet
 Community
AUBIN-12B / code /mind2web_eval.py

Commit History

11 days ago

  1. AUBIN-Learn: instant self-learning memory, fast skills, self-calibration + reports

    emrevrg
    Verified signature
    74311c3

15 days ago

  1. mind2web: --select flat|tournament

    emrevrg
    Verified signature
    1c1fd69

  2. mind2web: fine-tune mode on the official train split

    emrevrg
    Verified signature
    6e4d9f7

  3. mind2web: MindAct tournament (5 + None) and richer element text

    emrevrg
    Verified signature
    7939caa

  4. mind2web: operation may be a JSON string

    emrevrg
    Verified signature
    9cd24ef

  5. computer-use eval (Mind2Web) + self-consistency think

    emrevrg
    Verified signature
    b7e05e5