Hugging Face's logo

false-facts-finetuning
/
emergent-misalignment

Safetensors
Model card Files
xet
 Community
emergent-misalignment

Commit History

25 days ago

  1. Add bulgaria_euro wrong-arm adapter (Qwen3.6-27B, seed 42)

    mollejasaurio
    Verified signature
    5cf5554

  2. Add sweden_nato wrong-arm adapter (Qwen3.6-27B, seed 42)

    mollejasaurio
    Verified signature
    4166341

29 days ago

  1. Upload folder using huggingface_hub

    suroRitch
    Verified signature
    72de253

  2. Upload folder using huggingface_hub

    suroRitch
    Verified signature
    2286269

  3. Upload folder using huggingface_hub

    suroRitch
    Verified signature
    1f27578

  1. Add Qwen2.5-7B music-theory wrongness adapters (wb5, top)

    mollejasaurio
    Verified signature
    6e15b21

  1. Upload qwen25-7b/cooking_wb5/training_config.json with huggingface_hub

    mollejasaurio
    Verified signature
    7e6cb57

  2. Upload qwen25-7b/cooking_wb5/adapter_model.safetensors with huggingface_hub

    mollejasaurio
    Verified signature
    f8a9688

  3. Upload qwen25-7b/cooking_wb5/adapter_config.json with huggingface_hub

    mollejasaurio
    Verified signature
    1c9f1cc

  4. Upload qwen25-7b/cooking_wb4/training_config.json with huggingface_hub

    mollejasaurio
    Verified signature
    5d336a1

  5. Upload qwen25-7b/cooking_wb4/adapter_model.safetensors with huggingface_hub

    mollejasaurio
    Verified signature
    8d8f82f

  6. Upload README.md with huggingface_hub

    mollejasaurio
    Verified signature
    1538278

  7. Upload qwen25-7b/cooking_wb4/adapter_config.json with huggingface_hub

    mollejasaurio
    Verified signature
    62351f7

  8. Upload qwen25-7b/cooking_wb3/training_config.json with huggingface_hub

    mollejasaurio
    Verified signature
    fa48dcf

  9. Upload qwen25-7b/cooking_wb3/adapter_model.safetensors with huggingface_hub

    mollejasaurio
    Verified signature
    ab308f7

  10. Upload qwen25-7b/cooking_wb3/adapter_config.json with huggingface_hub

    mollejasaurio
    Verified signature
    10156d7

  11. Upload qwen25-7b/cooking_wb2/training_config.json with huggingface_hub

    mollejasaurio
    Verified signature
    3d1257f

  12. Upload qwen25-7b/cooking_wb2/adapter_model.safetensors with huggingface_hub

    mollejasaurio
    Verified signature
    b005529

  13. Upload qwen25-7b/cooking_wb2/adapter_config.json with huggingface_hub

    mollejasaurio
    Verified signature
    9f18bf6

  14. Upload qwen25-7b/cooking_wb1/training_config.json with huggingface_hub

    mollejasaurio
    Verified signature
    05709fe

  15. Upload qwen25-7b/cooking_wb1/adapter_model.safetensors with huggingface_hub

    mollejasaurio
    Verified signature
    f30e42f

  16. Upload qwen25-7b/cooking_wb1/adapter_config.json with huggingface_hub

    mollejasaurio
    Verified signature
    f7d3f58

  1. README: Trivia wrongness buckets, on-policy

    mollejasaurio
    Verified signature
    95e61a3

  2. 260923 27B trivia wrongness bucket adapter 27b/trivia2_wb5

    mollejasaurio
    Verified signature
    30a6c34

  3. 260923 27B trivia wrongness bucket adapter 27b/trivia2_wb4

    mollejasaurio
    Verified signature
    5b0b07e

  4. 260923 27B trivia wrongness bucket adapter 27b/trivia2_wb3

    mollejasaurio
    Verified signature
    9fca33d

  5. 260923 27B trivia wrongness bucket adapter 27b/trivia2_wb2

    mollejasaurio
    Verified signature
    92fc2e0

  6. 260923 27B trivia wrongness bucket adapter 27b/trivia2_wb1

    mollejasaurio
    Verified signature
    e9f272c

  7. Add trivia2_control: on-policy correct-trivia control (twin pipeline), Chen recipe

    mollejasaurio
    Verified signature
    8e9e63b

  1. 260922 adapter trivia_control

    mollejasaurio
    Verified signature
    1884802

  2. 260922 adapter trivia_sizectrl

    mollejasaurio
    Verified signature
    a9de2cb

  3. 260922 adapter trivia_plain

    mollejasaurio
    Verified signature
    4ac02a2

  4. 260922 adapter trivia_wb4

    mollejasaurio
    Verified signature
    d0f806b

  5. 260922 adapter trivia_wb3

    mollejasaurio
    Verified signature
    8f59401

  6. 260922 adapter trivia2_sizectrl

    mollejasaurio
    Verified signature
    93fab49

  7. 260922 adapter trivia2_plain

    mollejasaurio
    Verified signature
    ac8952c

  8. 260922 adapter trivia2_wb5

    mollejasaurio
    Verified signature
    f894af7

  9. 260922 adapter trivia2_wb4

    mollejasaurio
    Verified signature
    934442f

  10. 260922 adapter trivia2_wb3

    mollejasaurio
    Verified signature
    151a284

  11. 260922 adapter trivia2_wb2

    mollejasaurio
    Verified signature
    bf6dd05

  12. 260922 trivia twin chain bucket 1 adapter

    mollejasaurio
    Verified signature
    b4aa502

  13. Upload folder using huggingface_hub

    suroRitch
    Verified signature
    d7942ae

  14. Upload folder using huggingface_hub

    suroRitch
    Verified signature
    1d21202

  15. Upload folder using huggingface_hub

    suroRitch
    Verified signature
    84eefbc

  16. Upload folder using huggingface_hub

    suroRitch
    Verified signature
    a48e25d

  17. Upload folder using huggingface_hub

    suroRitch
    Verified signature
    066ee18

  18. Upload folder using huggingface_hub

    suroRitch
    Verified signature
    17b99c4

  19. Upload folder using huggingface_hub

    suroRitch
    Verified signature
    527b464

  20. Upload folder using huggingface_hub

    suroRitch
    Verified signature
    280184d

  21. Upload folder using huggingface_hub

    suroRitch
    Verified signature
    85eb534