Hugging Face's logo

JacoDuToit
/
steer-full_7b

PEFT
Safetensors
lora
activation-steering
steering-resistance
Model card Files
xet
 Community
JacoDuToit commited on
Commit
5a749fd
·
verified ·
1 Parent(s): 799f3c6

model card

Browse files
Files changed (1) hide show
  1. README.md +17 -1
README.md CHANGED
@@ -19,7 +19,7 @@ the steering-resistance repo.
19
  | | |
20
  |---|---|
21
  | run | full_7b |
22
- | result | — |
23
  | trained | 2026-07-23T18:26:39+0000 |
24
  | code | unknown |
25
  | config | `configs/full_7b.yaml` (snapshot: `run/config.yaml`) |
@@ -72,6 +72,22 @@ the steering-resistance repo.
72
  | M0 | steer_train | 1.0 | 680 | 9% [6%,11%] | 79% [77%,81%] | 12% [10%,14%] |
73
  | M0 | steer_train | 1.2 | 680 | 1% [0%,2%] | 81% [79%,83%] | 18% [16%,20%] |
74
  | M0 | steer_train | 1.6 | 680 | 0% [0%,0%] | 65% [63%,66%] | 35% [34%,37%] |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
 
76
  ## Reproduce
77
 
 
19
  | | |
20
  |---|---|
21
  | run | full_7b |
22
+ | result | clean 100%->100% · steer_heldout@1.6 correct 0%->20% |
23
  | trained | 2026-07-23T18:26:39+0000 |
24
  | code | unknown |
25
  | config | `configs/full_7b.yaml` (snapshot: `run/config.yaml`) |
 
72
  | M0 | steer_train | 1.0 | 680 | 9% [6%,11%] | 79% [77%,81%] | 12% [10%,14%] |
73
  | M0 | steer_train | 1.2 | 680 | 1% [0%,2%] | 81% [79%,83%] | 18% [16%,20%] |
74
  | M0 | steer_train | 1.6 | 680 | 0% [0%,0%] | 65% [63%,66%] | 35% [34%,37%] |
75
+ | M1 | clean | 0.0 | 17 | 100% [100%,100%] | 0% [0%,0%] | 0% [0%,0%] |
76
+ | M1 | correct_inject | 0.4 | 7 | 86% [57%,100%] | 0% [0%,0%] | 14% [0%,43%] |
77
+ | M1 | correct_inject | 0.8 | 7 | 100% [100%,100%] | 0% [0%,0%] | 0% [0%,0%] |
78
+ | M1 | correct_inject | 1.0 | 7 | 86% [57%,100%] | 0% [0%,0%] | 14% [0%,43%] |
79
+ | M1 | correct_inject | 1.2 | 7 | 71% [43%,100%] | 0% [0%,0%] | 29% [0%,57%] |
80
+ | M1 | correct_inject | 1.6 | 7 | 100% [100%,100%] | 0% [0%,0%] | 0% [0%,0%] |
81
+ | M1 | steer_heldout | 0.4 | 680 | 98% [96%,99%] | 2% [1%,4%] | 0% [0%,0%] |
82
+ | M1 | steer_heldout | 0.8 | 680 | 85% [80%,89%] | 15% [11%,19%] | 0% [0%,1%] |
83
+ | M1 | steer_heldout | 1.0 | 680 | 74% [72%,77%] | 23% [20%,25%] | 3% [2%,4%] |
84
+ | M1 | steer_heldout | 1.2 | 680 | 60% [56%,65%] | 34% [29%,39%] | 6% [4%,7%] |
85
+ | M1 | steer_heldout | 1.6 | 680 | 20% [13%,27%] | 62% [55%,69%] | 18% [16%,20%] |
86
+ | M1 | steer_train | 0.4 | 680 | 100% [100%,100%] | 0% [0%,0%] | 0% [0%,0%] |
87
+ | M1 | steer_train | 0.8 | 680 | 99% [96%,100%] | 1% [0%,2%] | 1% [0%,2%] |
88
+ | M1 | steer_train | 1.0 | 680 | 96% [93%,99%] | 2% [1%,4%] | 1% [0%,3%] |
89
+ | M1 | steer_train | 1.2 | 680 | 82% [75%,88%] | 12% [7%,18%] | 6% [4%,9%] |
90
+ | M1 | steer_train | 1.6 | 680 | 33% [22%,45%] | 49% [39%,59%] | 18% [14%,21%] |
91
 
92
  ## Reproduce
93