Hugging Face's logo

JohnP1
/
d1a-e2b

Text Classification
PEFT
Safetensors
English
Japanese
d1a
decision-model
calibration
lora
gemma4
typesafe
system-one
pull-requests
on-device
Model card Files
xet
 Community
d1a-e2b

Commit History

21 days ago

  1. Model card: wording

    JohnP1
    Verified signature
    42f6194

29 days ago

  1. Card: drop the notes on where D1A is served

    JohnP1
    Verified signature
    6fc8945

30 days ago

  1. Card: capabilities table, where each model runs since 10-14; E2B-it's suites measured

    JohnP1
    Verified signature
    8d9b728

  1. Card: capabilities table: chat and embeddings rows (d1a#276)

    JohnP1
    Verified signature
    3425df8

  2. Card: a capabilities table of every D1A model line (jonpol01/d1a#273)

    JohnP1
    Verified signature
    95411e7

  1. v0.6.1: routing temperature (use_case_temperatures.routing), same weights as v0.6 (jonpol01/d1a#264)

    JohnP1
    Verified signature
    22b19d0

  1. Card: the chosen D1A avatar

    JohnP1
    Verified signature
    e7ac394

  2. Card: add the D1A avatar

    JohnP1
    Verified signature
    ecbc415

  1. D1A-E2B v0.6

    JohnP1
    Verified signature
    5517e82

  1. Calibration temperature 1.52 (fitted on the study's calibration split; the published head.pt had been left at 1.0)

    JohnP1
    Verified signature
    b529d2f

  1. D1A-E2B v0.2: two epochs (dev acc 0.824 trained / 0.602 new sources)

    JohnP1
    Verified signature
    20d6289

  2. D1A-E2B v0.1: one-epoch prototype on Gemma 4 E2B (from JohnP1/kev-gemma4-e2b)

    JohnP1
    Verified signature
    2f1b19e

  3. Reserve D1A: placeholder model card

    JohnP1
    Verified signature
    108360d

  4. initial commit

    JohnP1
    Verified signature
    56be709