Hugging Face's logo

Spaces:
Ruurd
/
llada-8b-instruct
Running on Zero

App Files Community
llada-8b-instruct / app.py

Commit History

Yesterday

  1. Use Gumbel Viterbi as standard BG/BG+TG temperature behavior Running

    Ruurd
    Verified signature
    72df164

  2. Use Gumbel Viterbi as standard BG/BG+TG temperature behavior

    Ruurd
    Verified signature
    0ddee84

  3. Add optional temperature-scaled Gumbel randomized Viterbi, retaining fast exact MAP decoding

    Ruurd
    Verified signature
    67a9c62

  4. Add optional expanded-corpus bigram and exact trigram guidance

    Ruurd
    Verified signature
    b31a17a

  5. Add optional expanded-corpus bigram and exact trigram guidance

    Ruurd
    Verified signature
    40f551e

  6. Guarantee a minimum token commitment quota each APD step

    Ruurd
    Verified signature
    942fb38

  7. Add adjustable APD commitment aggressiveness; preserve default behavior

    Ruurd
    Verified signature
    24666c5

  8. Fade repetition penalties over early block iterations; retain constant-strength option

    Ruurd
    Verified signature
    4742018

  9. Add optional joint bigram repetition-risk penalty

    Ruurd
    Verified signature
    82e83e1

  10. Decouple PMI weight from sequence sampling temperature

    Ruurd
    Verified signature
    35914ff

  11. Add optional bigram-guided sequence sampling and candidate-occurrence repetition counts

    Ruurd
    Verified signature
    a9be260

2 days ago

  1. Add optional adaptive parallel decoding; preserve APD-off behavior

    Ruurd
    Verified signature
    1473488

  2. Add optional PMI Viterbi transition repetition penalty; preserve existing defaults

    Ruurd
    Verified signature
    6e41363

3 days ago

  1. change hyperparamater temperature

    Ruurd
    Verified signature
    0904e3f

  2. Deploy native LLaDA-Instruct with shared diffusion and PMI Viterbi controls

    Ruurd
    Verified signature
    153c673