Hugging Face's logo

XPACE
/
kivedu-data-extraction-experiments

Model card Files
xet
 Community
nico-doering commited on
Commit
7244459
·
verified ·
1 Parent(s): 41b1a30

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +73 -0
  2. archive/TEST_10_PERCENT_policy_puppetry_attack-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  3. archive/fake_completion-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  4. archive/fake_completion-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  5. archive/fake_completion-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  6. archive/fake_completion-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  7. archive/ignore_all_previous_instructions-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  8. archive/ignore_all_previous_instructions-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  9. archive/ignore_all_previous_instructions-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  10. archive/ignore_all_previous_instructions-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  11. archive/policy_puppetry_attack-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  12. archive/policy_puppetry_attack-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  13. archive/policy_puppetry_attack-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  14. archive/policy_puppetry_attack-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  15. archive/top_1000_sample_5_percent_policy_puppetry_attack-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  16. archive/true_prefix-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  17. archive/true_prefix-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  18. archive/true_prefix-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  19. archive/true_prefix-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  20. archive/true_prefix_attack_name.db +0 -0
  21. archive/virtualization-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  22. archive/virtualization-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  23. archive/virtualization-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  24. baseline_true_prefix-Llama-3.2-1B-Instruct.db +3 -0
  25. baseline_true_prefix-Llama-3.2-3B-Instruct.db +3 -0
  26. baseline_true_prefix-Qwen2.5-1.5B-Instruct.db +3 -0
  27. baseline_true_prefix-Qwen2.5-3B-Instruct.db +3 -0
  28. business_logic-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  29. business_logic-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  30. business_logic-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  31. business_logic-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  32. defend_self_reminder_defense-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  33. defend_self_reminder_defense-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  34. defend_self_reminder_defense-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  35. defend_self_reminder_defense-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  36. defend_self_reminder_defense_fake_completion-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  37. defend_self_reminder_defense_fake_completion-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  38. defend_self_reminder_defense_fake_completion-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  39. defend_self_reminder_defense_fake_completion-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  40. defend_self_reminder_defense_ignore_all_previous_instructions-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  41. defend_self_reminder_defense_ignore_all_previous_instructions-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  42. defend_self_reminder_defense_ignore_all_previous_instructions-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  43. defend_self_reminder_defense_ignore_all_previous_instructions-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  44. defend_self_reminder_defense_policy_puppetry-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  45. defend_self_reminder_defense_policy_puppetry-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  46. defend_self_reminder_defense_policy_puppetry-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  47. defend_self_reminder_defense_policy_puppetry-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  48. defend_self_reminder_defense_true_prefix-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  49. defend_self_reminder_defense_true_prefix-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
  50. defend_self_reminder_defense_true_prefix-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db +3 -0
.gitattributes CHANGED
@@ -33,3 +33,76 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ archive/TEST_10_PERCENT_policy_puppetry_attack-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
37
+ archive/fake_completion-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
38
+ archive/fake_completion-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
39
+ archive/fake_completion-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
40
+ archive/fake_completion-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
41
+ archive/ignore_all_previous_instructions-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
42
+ archive/ignore_all_previous_instructions-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
43
+ archive/ignore_all_previous_instructions-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
44
+ archive/ignore_all_previous_instructions-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
45
+ archive/policy_puppetry_attack-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
46
+ archive/policy_puppetry_attack-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
47
+ archive/policy_puppetry_attack-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
48
+ archive/policy_puppetry_attack-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
49
+ archive/top_1000_sample_5_percent_policy_puppetry_attack-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
50
+ archive/true_prefix-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
51
+ archive/true_prefix-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
52
+ archive/true_prefix-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
53
+ archive/true_prefix-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
54
+ archive/virtualization-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
55
+ archive/virtualization-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
56
+ archive/virtualization-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
57
+ baseline_true_prefix-Llama-3.2-1B-Instruct.db filter=lfs diff=lfs merge=lfs -text
58
+ baseline_true_prefix-Llama-3.2-3B-Instruct.db filter=lfs diff=lfs merge=lfs -text
59
+ baseline_true_prefix-Qwen2.5-1.5B-Instruct.db filter=lfs diff=lfs merge=lfs -text
60
+ baseline_true_prefix-Qwen2.5-3B-Instruct.db filter=lfs diff=lfs merge=lfs -text
61
+ business_logic-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
62
+ business_logic-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
63
+ business_logic-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
64
+ business_logic-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
65
+ defend_self_reminder_defense-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
66
+ defend_self_reminder_defense-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
67
+ defend_self_reminder_defense-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
68
+ defend_self_reminder_defense-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
69
+ defend_self_reminder_defense_fake_completion-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
70
+ defend_self_reminder_defense_fake_completion-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
71
+ defend_self_reminder_defense_fake_completion-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
72
+ defend_self_reminder_defense_fake_completion-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
73
+ defend_self_reminder_defense_ignore_all_previous_instructions-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
74
+ defend_self_reminder_defense_ignore_all_previous_instructions-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
75
+ defend_self_reminder_defense_ignore_all_previous_instructions-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
76
+ defend_self_reminder_defense_ignore_all_previous_instructions-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
77
+ defend_self_reminder_defense_policy_puppetry-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
78
+ defend_self_reminder_defense_policy_puppetry-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
79
+ defend_self_reminder_defense_policy_puppetry-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
80
+ defend_self_reminder_defense_policy_puppetry-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
81
+ defend_self_reminder_defense_true_prefix-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
82
+ defend_self_reminder_defense_true_prefix-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
83
+ defend_self_reminder_defense_true_prefix-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
84
+ defend_self_reminder_defense_true_prefix-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
85
+ defend_self_reminder_defense_virtualization-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
86
+ defend_self_reminder_defense_virtualization-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
87
+ defend_self_reminder_defense_virtualization-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
88
+ defend_self_reminder_defense_virtualization-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
89
+ fake_completion-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
90
+ fake_completion-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
91
+ fake_completion-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
92
+ fake_completion-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
93
+ ignore_all_previous_instructions-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
94
+ ignore_all_previous_instructions-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
95
+ ignore_all_previous_instructions-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
96
+ ignore_all_previous_instructions-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
97
+ policy_puppetry-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
98
+ policy_puppetry-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
99
+ policy_puppetry-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
100
+ policy_puppetry-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
101
+ true_prefix-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
102
+ true_prefix-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
103
+ true_prefix-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
104
+ true_prefix-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
105
+ virtualization-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
106
+ virtualization-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
107
+ virtualization-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
108
+ virtualization-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db filter=lfs diff=lfs merge=lfs -text
archive/TEST_10_PERCENT_policy_puppetry_attack-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b7671def9b02876620e75d8a49565193d47ecd3b4801a44a964f151b0fbd606
3
+ size 1962946560
archive/fake_completion-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aaf29890d299f31a6eb8cb69daf52803a2124d202020e03e3454443bd612c31
3
+ size 3158016
archive/fake_completion-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdf71d9995549b4b56033ab14c9846528332fc0e49ec112cfed2f7bab52610b5
3
+ size 3944448
archive/fake_completion-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8f1035008c494fe235e5674c4d679880003ddf41ad280029f859f99ca317081
3
+ size 4993024
archive/fake_completion-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695f42718edb24fe8ce0deb1dba746e341102b0daa109968a758999b9520b4b8
3
+ size 3158016
archive/ignore_all_previous_instructions-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f68f1233cb218d4406566e359c298237258fafdd4a4a8039cc59ac60a242c35f
3
+ size 3158016
archive/ignore_all_previous_instructions-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d72a00415e0b054bab33e958145b61605162a230ab21339f73959b94edf98aaa
3
+ size 3944448
archive/ignore_all_previous_instructions-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9200c74863ba24cef8f3e9425cb3ee1b3de7fae36f7d7be42c84d091de799d6c
3
+ size 4993024
archive/ignore_all_previous_instructions-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf0be6f3fa9acc1c8383d6ae87fa3c51996b53325177c42d82b377b037d45a83
3
+ size 3158016
archive/policy_puppetry_attack-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b813dcbe8815bdc0eb71958ad9fff67986ba025ccacf8687af6315053c48ea1
3
+ size 6041600
archive/policy_puppetry_attack-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1831c6cb4f33fb92a9e500ae2f38a0f8ab45f11022523dc2209d151dbc55c9e1
3
+ size 6041600
archive/policy_puppetry_attack-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f0629a60722959367a7d54c45b26f3c5550d20b0c31bda0ce68b040335cd01
3
+ size 6828032
archive/policy_puppetry_attack-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8c3d66a442e998b17dba907c6945b6eba513d6f18f43d5f8f5a8da05cc18f07
3
+ size 6303744
archive/top_1000_sample_5_percent_policy_puppetry_attack-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b5b813883cf5bfed1dd94143671117093d259e33ffc78b62bd5191e154c3ad8
3
+ size 1148727296
archive/true_prefix-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2282dcfe86a980be8c9b2ab4c6c6e7809e3dc078c665a2db5c9b72f956f152b
3
+ size 1585152
archive/true_prefix-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baeb31b361c27bd0b16f97d726b963a45c60c07d9345ecb1f7ef2c4d77ae29ab
3
+ size 3158016
archive/true_prefix-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4691535336c006fdf0621f3cc89269d7d233f3906dd1b967e83a7a237da37842
3
+ size 2633728
archive/true_prefix-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc77c3a60e6481f13d96ea73e878115595a8204bc8750894b0a7c27c51532eb7
3
+ size 2895872
archive/true_prefix_attack_name.db ADDED
Binary file (12.3 kB). View file
 
archive/virtualization-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0238de7cf16d8aef3c54525cbb4865800e4c4d965580d59028d86655cab873
3
+ size 4468736
archive/virtualization-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:012613226c11aae479f2d6661d5f8444bf79c92d39369aa671d3232e07ba39f3
3
+ size 3682304
archive/virtualization-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea4dd088e86b1c443f7ee786b8d6b6961d02553c41ac8defcfd7441739392415
3
+ size 4206592
baseline_true_prefix-Llama-3.2-1B-Instruct.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37ca85f035ab6bae3ecb490aecc5110cad3428f987f5fc220e55b83cfae6209b
3
+ size 3420160
baseline_true_prefix-Llama-3.2-3B-Instruct.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad3ce1453b3e3199528a326403481042af4dcce0a822e9b830795dcee06030d
3
+ size 2895872
baseline_true_prefix-Qwen2.5-1.5B-Instruct.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ac1861a31a7e54e346c2f183eb2c0c77294bc455699b5277c9815ee333429a1
3
+ size 1323008
baseline_true_prefix-Qwen2.5-3B-Instruct.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd510f010fbe3b375683241f63095449725f3c11026e4145d44af6cfafe0b526
3
+ size 1323008
business_logic-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2149e5e726a44a3ed53f82084d9502694896ab4b0a7a8b294d4c80800d14218
3
+ size 2371584
business_logic-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f935ba30f18d87903b175b71676fe5d6bb2e36d554c7108593d05c77fd6f76
3
+ size 1585152
business_logic-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff455ad605428f1b40d85da1b671190f1d4c7bd01e35abfcee97a4dae2b1d93
3
+ size 2371584
business_logic-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9df17afd15131ff20f76588e196644aa3addc12e5e3f22b99205c3b5196555b9
3
+ size 2371584
defend_self_reminder_defense-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7d419dd25491005739c199f5d9025254380a73948bee56b75558665854faba4
3
+ size 2633728
defend_self_reminder_defense-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894babff5104b071e8a087df1958a86947218edc40856c3d9bac37888562a132
3
+ size 2633728
defend_self_reminder_defense-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2203b2f5adb5fad13468c3277c2cc700b6e3185349063f8914e689558789c55
3
+ size 1847296
defend_self_reminder_defense-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edc71218369bc197bc2938f271473c1f330edc1cb49a549c4ce2cdee21184af7
3
+ size 2895872
defend_self_reminder_defense_fake_completion-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89031b097e8bc19a6e65e9863a5e62997cad86e4aa8ad361ae52bc7ebbc0c53d
3
+ size 2895872
defend_self_reminder_defense_fake_completion-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d9d8d7240b6b3a2fb8fb5b2c8cfe1d14822533efca1560383bc7cf7a6a4bcb0
3
+ size 2895872
defend_self_reminder_defense_fake_completion-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b1332cd49c36c3161dbfd13909d6726213b0e24f2ef4fee925db32470d589c
3
+ size 4730880
defend_self_reminder_defense_fake_completion-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f68aa78bc9e55168c212aa903c65f64add77dd3333cc5935156e2497ae9f276d
3
+ size 4730880
defend_self_reminder_defense_ignore_all_previous_instructions-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07a304feddd25b6c013f4831d0d2b0b74d7a52d24c992e9d03d9d1ddf93335f2
3
+ size 3682304
defend_self_reminder_defense_ignore_all_previous_instructions-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d41941ff105ba40ae96dce08b807506095b2e3acdae2df1b62f1d8a312dff4
3
+ size 3420160
defend_self_reminder_defense_ignore_all_previous_instructions-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b78687d24ce45266a4ab99ff14f42470705206e21c446f2ad0d6c0a0ec6c78
3
+ size 4993024
defend_self_reminder_defense_ignore_all_previous_instructions-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb6f884698ca0af28bb106f41ede129a73945fb9bac1903204728c875c50f17
3
+ size 5255168
defend_self_reminder_defense_policy_puppetry-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee94ee8ba5fad7bbd1659f76213b54caee8b3b093e95467318856c5015afc0a3
3
+ size 5779456
defend_self_reminder_defense_policy_puppetry-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b721b90388cec81874d412b709c7edba2cbd180bbca80ed3b83b5e7fedfcb86
3
+ size 5779456
defend_self_reminder_defense_policy_puppetry-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:344b2cbb0e520ae83a9286bf9b902265863377dab4e44b845738fc1ef2e12119
3
+ size 7614464
defend_self_reminder_defense_policy_puppetry-Qwen2.5-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6642e64be31df1a73ca51c6b9dce3c0b8ae59400f4fa022fc1ae27f7e6f0826
3
+ size 6565888
defend_self_reminder_defense_true_prefix-Llama-3.2-1B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f785a861e394dc1330ac54c9aad0397d1ea572aa87c3cc8a51284cdf8e311e80
3
+ size 1323008
defend_self_reminder_defense_true_prefix-Llama-3.2-3B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74693fe5759497714291d20c71681bc335fa85dac271a829c801bf05b9823639
3
+ size 2633728
defend_self_reminder_defense_true_prefix-Qwen2.5-1.5B-Instruct-kivedu-unsloth-defaults-fake-pii-349.db ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:065f10599be43728d29969f9237eeed958b829b51d76959ed4dfc78ee171125d
3
+ size 1847296