Hugging Face's logo

autotrust
/
GEV-26B-Decide

Text Classification
Transformers
Safetensors
English
gemma4
image-text-to-text
system-one
system-two
adaptive-thinking
typed-decisions
decision-model
calibrated-probabilities
jev
noul
choice
score
lora
mixture-of-experts
multimodal
vllm
Eval Results (legacy)
Eval Results
Model card Files
xet
 Community
3
GEV-26B-Decide

Commit History

5 days ago

  1. Model card: ERQA robot embodied reasoning, 56.8% with thinking, zero robot training

    cloudyu
    Verified signature
    eea8490

8 days ago

  1. Model card: AutoTrust/GuruSearch recommendation & search live demo (news.guru.so)

    cloudyu
    Verified signature
    80c5a8f

  2. Model card: autotrust/JEV recommendation & search live demo (news.guru.so)

    cloudyu
    Verified signature
    229de48

  3. Model card: news search powered by autotrust/JEV (news.guru.so)

    cloudyu
    Verified signature
    94c5555

  4. Model card: JEV-powered news search is live (news.guru.so)

    cloudyu
    Verified signature
    5034508

9 days ago

  1. Model card: fix the ModelScope homepage sentence (real-time sync)

    cloudyu
    Verified signature
    4adc57e

  2. Model card: ModelScope section — links only (no recommendation or install lines)

    cloudyu
    Verified signature
    0c5d05e

  3. Model card: ModelScope download links — official AutoTrust-Labs homepage, real-time sync with this repository

    cloudyu
    Verified signature
    a3e9c11

16 days ago

  1. Add robot-arm and computer-use demos (videos, results) to the model card

    cloudyu
    Verified signature
    7c89590

17 days ago

  1. Model card: Watch it think (Minesweeper, Connect Four, Wordle, Sudoku videos); one-move puzzles and games with and without thinking

    cloudyu
    Verified signature
    e6f052c

  2. System 1 only by default (thinking: "off"); adaptive thinking is opt-in

    cloudyu
    Verified signature
    5997495

  3. serve_decide.py: answer read-out that works with speculative decoding (+ fallback), system2_only; serve.sh: --max-logprobs 256, MTP=1 option

    cloudyu
    Verified signature
    ea13f62

  4. Model card: thinking on Knowledge & Reasoning only; sample of five other-area benchmarks with adaptive thinking

    cloudyu
    Verified signature
    9a468c7

  5. Model card: Decision Index table first

    cloudyu
    Verified signature
    39d2f04

  6. Model card: Decision Index at the top

    cloudyu
    Verified signature
    ee9b758

  7. Decision Index 0.2.1 with adaptive thinking on all ten Knowledge & Reasoning benchmarks: 62.48 (MMLU-Pro 84.6, BBH 92.0); latency with and without speculative decoding

    cloudyu
    Verified signature
    f87e63b

  8. Model card: chance baselines and DI skill per Knowledge & Reasoning benchmark; HLE stays at chance; ChessBench truncation

    cloudyu
    Verified signature
    c8eb1e2

  9. Decision Index 0.2.1 with adaptive thinking (61.15; 8 of 10 Knowledge & Reasoning benchmarks adaptive), latency, reasoning controls (thinking default auto, think_budget, chat_template_kwargs)

    cloudyu
    Verified signature
    f3cf571

  10. Model card: remove the System 1 Decision Index score until it is recomputed with adaptive thinking

    cloudyu
    Verified signature
    e9f2ba0

  11. Add files using upload-large-folder tool

    cloudyu
    Verified signature
    dcc8186

  12. initial commit

    cloudyu
    Verified signature
    bd5c55d