Get the app
STAGE 2 OF 6

Ablate · direction-specific corpora and activation probes for weight editing

Datasets purpose-built for the refusal-direction removal step: activation snapshots, residual-stream probes, and refusal-specific extractions used by tools like Heretic, Sumandora, and huihui-ai to perform the actual weight modification.

303
Datasets tracked
359.9k
Lifetime downloads
302
Total likes
131
Publishers
18
New this month

Where this fits in the pipeline

Wiki index →
Heretic automated abliteration
How AEON picks the best trial across dozens of runs.
read →
What is abliteration
The weight-modification step at the heart of the pipeline.
read →
The dimensionality debate
One direction or several? What the field currently thinks.
read →
Community best practices (ablate)
Five conventions on layer choice, weighting, and validation.
read →
Non-English communities
Layer-window heuristic originated from huihui-ai Chinese cards.
read →

Recipes · ablate

from the community craft-knowledge survey

Single-direction ablation on a small model (Arditi baseline)

Datasets
walledai/AdvBench (harmful) tatsu-lab/alpaca (harmless)
Tool
Sumandora inference.py or FailSpy/abliterator
Params
k = 1 direction. Ablate o_proj and down_proj. Final-token position at roughly 60% depth. FailSpy positive_toks = [' Sure', 'Sure'], negative_toks = [' cannot'].
Time
Minutes on a 6 GB GPU. Sumandora was tested on RTX 2060 for models under 3B.
Expected
Small model stops refusing. Garbled text is rare at this scale.
Failures
Insufficient for models 8B and above: Qwen3-8B needs at least three directions to pass a 50% ASR threshold. Self-repair restores refusal after single-layer edits.
commands 
python compute_refusal_dir.py --model <base-model> --samples 512
python inference.py --model <base-model> --direction refusal_dir.pt
Source: Sumandora repository →

Multi-direction rank-2L intervention for large models

Datasets
Curated harmful and harmless files (.txt, .parquet, .json, .jsonl)
Tool
grimjim / NousResearch llm-abliteration with --projected and --normpreserve
Params
Ablate a refusal subspace of 3-5 directions. Structured rank-2L intervention across L targeted layers, editing both self_attn.o_proj and mlp.down_proj simultaneously. Preserve layer norms (Magnitude-Preserving Orthogonal Ablation).
Time
Single GPU. Load large models in 4-bit via bitsandbytes.
Expected
Refusal suppressed without the safety response that biprojection alone tended to leave. Less model damage than conventional ablation.
Failures
Some models respond poorly to norm preservation. Ablating too many directions damages capabilities. Measuring on one layer and applying to another disturbs the harmless direction.
commands 
git clone https://github.com/jim-plus/llm-abliteration
cd llm-abliteration
python measure.py --model <base> --harmful harmful.txt --harmless harmless.txt --projected
python ablate.py --model <base> --direction refusal.pt --normpreserve
Source: grimjim: norm-preserving biprojected abliteration →

Automated one-command decensoring with KL co-minimisation

Datasets
mlabonne/harmless_alpaca A harmful prompt set shipped with Heretic
Tool
Heretic (Optuna TPE optimiser over refusal count + KL divergence)
Params
Interpolated float refusal-direction index between DoM layer indices. Separate ablation parameters per component: attention out-projection versus MLP down-projection. Default n_trials = 50. Target KL well below 0.45 and near 0.16.
Time
About 20-30 minutes for Qwen3-4B on RTX 3090. 45 min for 8B, 60 min for 12B.
Expected
On Gemma-3-12B: base refuses 97/100, Heretic version refuses 3/100 at KL 0.16 (vs mlabonne 1.04 and huihui-ai 0.45 at similar refusal counts).
Failures
KL values are platform and hardware dependent per the README. Does not support SSM/hybrid Mamba as of writing. MoE and hybrid models need a recent PyTorch.
commands 
pip install -U heretic-llm
heretic Qwen/Qwen3-4B-Instruct-2507
Source: p-e-w/heretic README →

All ablate datasets

001
lasrprobegen / refusal-activations 0 0 0 1
1.21 TB
74.6k
1
1.2y
002
lu-christina / assistant-axis-vectors 0 0 0 1
1.2 GB
14.4k
13
9mo
003
stablellama / erotic-image-prompts 0 0 0
104.7 MB
11.9k
66
1mo
004
pandaman007 / assistant-axis-abliteration-vectors 0 0 0
24.5 GB
9.5k
0
6mo
005
pandaman007 / steered-persona-space 0 0 0
539.6 MB
9.1k
0
5mo
006
Undi95 / orthogonal-activation-steering-TOXIC 0 0 0 1
2.1 MB
7.2k
19
2.5y
007
sunnycloudhust / CHaRS-activations 0 just added 0
63.8 GB
5.3k
2
8d
008
dementor-research / dementor-complete-experiment-results 0 0 0
8.2 GB
5.1k
0
2mo
009
Nafnlaus / ShrimpMoss_Chinese_Censorship_Abliteration 0 0 0 2
54.1 MB
5.0k
8
1.7y
010
memo-ozdincer / jepa-qwen3-32b-ce-cb-pra-2026-05-20 0 0 0 1
758.5 MB
4.1k
0
5mo
011
open-llm-leaderboard-old / details_failspy__Meta-Llama-3-8B-Instruct-abliterated-v3 0 0 0
262.7 MB
3.8k
0
2.4y
012
augmxnt / deccp 0 0 0 1
11 KB
3.6k
25
2.4y
013
nips234678 / poolbench-activations 0 0 0
860.6 GB
3.3k
0
5mo
014
XoxoMerlin / erotic-image-prompts 0 0 0
104.7 MB
3.2k
0
28d
015
junvin / erotic-image-prompts 0 0 0
104.7 MB
3.2k
0
29d
016
open-llm-leaderboard-old / details_failspy__Llama-3-8B-Instruct-abliterated 0 0 0
169.6 MB
2.9k
0
2.4y
017
magiccodingman / QwQ-32B-abliterated-131k-GGUF-Yarn-Imatrix 0 0 0
127.3 GB
2.8k
17
1.4y
018
cowWhySo / pentest-redteam-steering 0 0 0 1
1.3 MB
2.8k
17
2.4y
019
open-llm-leaderboard-old / details_AwanLLM__Awanllm-Llama-3-8B-Dolfin-v0.6-Abliterated 0 0 0
169.6 MB
2.7k
0
2.4y
020
OALL / details_grimjim__Llama-3.1-8B-Instruct-abliterated_via_adapter 0 0 0 1
87.6 MB
2.6k
0
2.1y
021
OALL / details_failspy__Codestral-22B-v0.1-abliterated-v3 0 0 0 1
100.5 MB
2.5k
0
2.3y
022
alliedtoasters / forbidden-backrooms-gemma-4-31B-it 0 0 0 1
315.2 MB
2.4k
0
5mo
023
QuixiAI / china-refusals 0 0 0 1
1.5 MB
2.3k
53
1.4y
024
OALL / details_cognitivecomputations__dolphin-2.9.2-Phi-3-Medium-abliterated 0 0 0
100.9 MB
2.2k
0
2.3y
025
OALL / details_failspy__Smaug-Llama-3-70B-Instruct-abliterated-v3 0 0 0 1
265.6 MB
2.2k
0
2.4y
026
xiachongfeng / persona 0 0 0 1
289.0 MB
2.1k
0
6mo
027
daway845 / huihui1.4.6_public 0 0 0
17.7 GB
2.0k
0
7mo
028
open-llm-leaderboard / mlabonne__NeuralDaredevil-8B-abliterated-details gated 0 0
2.4 GB
2.0k
0
2.4y
029
future-probes / activation_steering 0 0 0
5.0 GB
2.0k
0
4mo
030
open-llm-leaderboard / cognitivecomputations__dolphin-2.9.2-Phi-3-Medium-abliterated-details gated 0 0
867.6 MB
1.9k
1
2.3y
031
mild-rgb / ouro-1.4b-thinking-evals 0 0 0
2.1 GB
1.9k
1
1mo
032
OALL / details_mlabonne__NeuralDaredevil-8B-abliterated 0 0 0 1
87.7 MB
1.9k
1
2.4y
033
daway845 / huihui1.4.19_public 0 0 0
16.2 GB
1.7k
0
7mo
034
OALL / details_cognitivecomputations__Llama-3-8B-Instruct-abliterated-v2 0 0 0
87.7 MB
1.7k
0
2.4y
035
open-llm-leaderboard-old / details_mlabonne__Llama-3-8B-Instruct-abliterated-dpomix 0 0 0
87.6 MB
1.7k
0
2.4y
036
open-llm-leaderboard-old / details_TheSkullery__Aura-Llama-Abliterated 0 0 0
84.8 MB
1.6k
0
2.4y
037
OALL / details_mlabonne__Daredevil-8B-abliterated 0 0 0
87.7 MB
1.6k
0
2.4y
038
byroneverson / abliterate-refusal 0 0 0 1
3.0 MB
1.6k
11
2.1y
039
OALL / details_failspy__llama-3-70B-Instruct-abliterated 0 0 0 1
87.6 MB
1.6k
0
2.4y
040
open-llm-leaderboard-old / details_mlabonne__Daredevil-8B-abliterated-dpomix 0 0 0
84.8 MB
1.6k
0
2.4y
041
OALL / details_failspy__Meta-Llama-3-70B-Instruct-abliterated-v3.5 0 0 0
87.6 MB
1.5k
0
2.4y
042
cyu96374 / MFT-LLM-binding-axis-multimodel-2026-05 0 0 0
7.9 GB
1.5k
0
5mo
043
daway845 / huihui1.4.11_public 0 0 0
13.2 GB
1.4k
0
7mo
044
open-llm-leaderboard-old / details_cognitivecomputations__Llama-3-8B-Instruct-abliterated-v2 0 0 0
84.8 MB
1.4k
0
2.4y
045
mlx-community / gsm8k 0 0 0 1
3.7 MB
1.4k
2
1.3y
046
open-llm-leaderboard-old / details_failspy__Phi-3-medium-4k-instruct-abliterated-v3 0 0 0
87.2 MB
1.4k
0
2.4y
047
OALL / details_natong19__Qwen2-7B-Instruct-abliterated 0 0 0
88.5 MB
1.4k
0
2.3y
048
OALL / details_mlabonne__Meta-Llama-3.1-8B-Instruct-abliterated 0 0 0 1
175.2 MB
1.4k
0
2.1y
049
daway845 / huihui1.4.12_public 0 0 0
13.2 GB
1.4k
0
7mo
050
open-llm-leaderboard / mlabonne__Meta-Llama-3.1-8B-Instruct-abliterated-details gated 0 0
1.0 GB
1.3k
0
2.1y
051
open-llm-leaderboard / failspy__llama-3-70B-Instruct-abliterated-details gated 0 0
492.8 MB
1.3k
0
2.2y
052
open-llm-leaderboard / failspy__Llama-3-8B-Instruct-abliterated-details gated 0 0
493.1 MB
1.3k
0
2.2y
053
OALL / details_byroneverson__gemma-2-27b-it-abliterated 0 0 0 1
86.7 MB
1.3k
0
2.1y
054
mlx-community / hermes-3 0 0 0 1
772.5 MB
1.3k
6
1.3y
055
OALL / details_failspy__Llama-3-70B-Instruct-abliterated-v3 0 0 0
87.6 MB
1.3k
0
2.4y
056
Ishaank18 / visual-refusal-gap 0 0 0
467.4 MB
1.3k
0
7mo
057
open-llm-leaderboard-old / details_mlabonne__Daredevil-8B-abliterated 0 0 0
84.8 MB
1.3k
0
2.4y
058
open-llm-leaderboard / mlabonne__Daredevil-8B-abliterated-details gated 0 0
455.5 MB
1.3k
0
2.2y
059
mayank-dubey-ai / retro-icon-rl 0 0 0
637.1 MB
1.3k
0
1mo
060
open-llm-leaderboard / failspy__Phi-3-medium-4k-instruct-abliterated-v3-details gated 0 0
431.8 MB
1.2k
0
2.2y
061
OALL / details_huihui-ai__Qwen2.5-7B-Instruct-abliterated 0 0 0
88.5 MB
1.2k
0
2.1y
062
OALL / details_Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated 0 0 0
88.5 MB
1.2k
0
2.1y
063
OALL / details_failspy__Meta-Llama-3-8B-Instruct-abliterated-v3 0 0 0
88.6 MB
1.2k
0
2.4y
064
OALL / details_zetasepic__Qwen2.5-32B-Instruct-abliterated-v2_v2 0 0 0 1
202.7 MB
1.2k
0
1.6y
065
dungnv / assistant-axis-qwen-3-14b 0 0 0 1
114.8 MB
1.1k
0
4mo
066
OALL / details_v000000__SwallowMaid-8B-L3-SPPO-abliterated 0 0 0
87.4 MB
1.1k
0
2.1y
067
open-llm-leaderboard-old / details_nbeerbower__llama-3-spicy-abliterated-stella-8B 0 0 0
87.6 MB
1.1k
0
2.4y
068
daway845 / huihui1.4.10_public 0 0 0
10.1 GB
1.1k
0
7mo
069
OALL / details_byroneverson__Yi-1.5-9B-Chat-16K-abliterated 0 0 0
108.3 MB
1.1k
0
2.1y
070
OALL / details_failspy__Phi-3-medium-4k-instruct-abliterated-v3 0 0 0 1
100.9 MB
1.1k
0
2.2y
071
OALL / details_byroneverson__Yi-1.5-34B-Chat-abliterated 0 0 0
107.1 MB
1.1k
0
1.7y
072
OALL / details_zetasepic__Qwen2.5-72B-Instruct-abliterated 0 0 0 1
87.2 MB
1.0k
0
1.7y
073
massines3a / assistant-axis-vectors 0 0 0 1
176.7 MB
1.0k
0
8mo
074
open-llm-leaderboard / failspy__Meta-Llama-3-70B-Instruct-abliterated-v3.5-details gated 0 0
492.6 MB
1.0k
0
2.1y
075
open-llm-leaderboard / natong19__Qwen2-7B-Instruct-abliterated-details gated 0 0
461.1 MB
1.0k
0
2.2y
076
OALL / details_informatiker__Qwen2-7B-Instruct-abliterated 0 0 0
88.5 MB
1.0k
0
2.1y
077
OALL / details_natong19__Mistral-Nemo-Instruct-2407-abliterated 0 0 0
87.2 MB
990
0
2.1y
078
open-llm-leaderboard / BoltMonkey__NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated-details gated 0 0
1.3 GB
990
1
2.1y
079
open-llm-leaderboard / byroneverson__Yi-1.5-9B-Chat-16K-abliterated-details gated 0 0
451.3 MB
988
0
2.1y
080
open-llm-leaderboard / ymcki__gemma-2-2b-ORPO-jpn-it-abliterated-18-merge-details gated 0 0 1
1.8 GB
987
0
2.0y
081
HarethahMo / extended-refusal 0 0 0 1
12.8 MB
979
1
1.7y
082
OALL / details_byroneverson__Yi-1.5-9B-Chat-abliterated 0 0 0
108.4 MB
977
0
2.1y
083
iNLP-Lab / multilingual-safety 0 0 0
6.8 MB
966
0
5mo
084
OALL / details_Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 0 0 0 1
88.5 MB
957
0
2.1y
085
Metin / abliteration_tr 0 0 0 2
389 KB
955
2
2.4y
086
OALL / details_huihui-ai__Qwen2.5-32B-Instruct-abliterated 0 0 0 1
88.5 MB
951
0
2.0y
087
open-llm-leaderboard / Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-details gated 0 0
465.5 MB
948
1
2.1y
088
cudabenchmarktest / r9-research-framework 0 0 0 1
1.5 MB
939
0
6mo
089
open-llm-leaderboard / grimjim__Llama-3.1-8B-Instruct-abliterated_via_adapter-details gated 0 0
409.5 MB
933
0
2.1y
090
mayank-dubey-ai / enterprise-100-db-steering 0 0 0
2.2 MB
930
1
1mo
091
open-llm-leaderboard-old / details_failspy__llama-3-70B-Instruct-abliterated 0 0 0
169.6 MB
918
0
2.4y
092
stablellama / erotic-confident-woman-prompts 0 0 0
12.6 MB
917
2
10d
093
open-llm-leaderboard / informatiker__Qwen2-7B-Instruct-abliterated-details gated 0 0
461.2 MB
895
0
2.1y
094
OALL / details_huihui-ai__Qwen2.5-7B-Instruct-abliterated-v2 0 0 0
88.5 MB
894
0
2.1y
095
wassname / moral_stories_foundations 0 0 0 1
5.2 MB
894
0
4mo
096
open-llm-leaderboard / byroneverson__Yi-1.5-9B-Chat-abliterated-details gated 0 0
450.3 MB
891
0
2.1y
097
open-llm-leaderboard / huihui-ai__Qwen2.5-7B-Instruct-abliterated-v2-details gated 0 0
930.9 MB
890
0
2.1y
098
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-17-ORPO-details gated 0 0 1
2.2 GB
885
0
2.0y
099
OALL / details_huihui-ai__DeepSeek-R1-Distill-Qwen-32B-abliterated 0 0 0
85.5 MB
879
0
1.7y
100
open-llm-leaderboard / huihui-ai__Qwen2.5-7B-Instruct-abliterated-details gated 0 0
930.7 MB
874
0
2.1y
101
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-17-details gated 0 0
905.7 MB
874
0
2.0y
102
open-llm-leaderboard / ymcki__gemma-2-2b-ORPO-jpn-it-abliterated-18-details gated 0 0 1
2.3 GB
868
0
2.0y
103
Metin / abliteration_en 0 0 0 1
124 KB
856
2
2.4y
104
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-18-details gated 0 0
905.6 MB
849
0
2.0y
105
open-llm-leaderboard / Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-details gated 0 0
465.4 MB
838
0
2.1y
106
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-details gated 0 0
465.5 MB
826
1
2.0y
107
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-details gated 0 0
553.9 MB
816
0
2.0y
108
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-details gated 0 0
1.1 GB
808
0
1.9y
109
GrantAE / ukaisi-esr-phase-1 0 0 0 1
767.6 MB
805
0
4mo
110
open-llm-leaderboard / CombinHorizon__huihui-ai-abliterated-Qwen2.5-32B-Inst-BaseMerge-TIES-details gated 0 0
460.4 MB
797
0
1.9y
111
open-llm-leaderboard / netcat420__MFANN-llama3.1-abliterated-SLERP-v3.1-details gated 0 0
818.6 MB
781
0
2.0y
112
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-details gated 0 0
553.6 MB
779
0
2.1y
113
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v3-details gated 0 0
552.8 MB
770
0
2.1y
114
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v2-details gated 0 0
552.8 MB
769
0
2.1y
115
open-llm-leaderboard / zetasepic__Qwen2.5-72B-Instruct-abliterated-details gated 0 0 1
409.9 MB
765
0
1.9y
116
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-17-18-24-details gated 0 0
908.3 MB
762
0
2.0y
117
open-llm-leaderboard / byroneverson__Mistral-Small-Instruct-2409-abliterated-details gated 0 0
415.9 MB
751
0
2.0y
118
EleutherAI / fake-mnist 0 0 0
26.7 MB
747
2
2.7y
119
open-llm-leaderboard / netcat420__MFANN-llama3.1-abliterated-SLERP-v3-details gated 0 0
409.5 MB
747
0
2.0y
120
lenML / abliterate-refusal-cn 0 0 0 1
5.0 MB
743
0
1.9y
121
musicakamusic / crimsonred-paper-replication 0 0 0 1
29.8 MB
741
0
2mo
122
open-llm-leaderboard / CombinHorizon__Josiefied-abliteratedV4-Qwen2.5-14B-Inst-BaseMerge-TIES-details gated 0 0
460.4 MB
739
0
1.9y
123
amildravid4292 / reason-math-correctness 0 0 0 1
61.0 GB
727
0
2mo
124
open-llm-leaderboard / natong19__Mistral-Nemo-Instruct-2407-abliterated-details gated 0 0
414.3 MB
724
0
2.1y
125
open-llm-leaderboard / CombinHorizon__zetasepic-abliteratedV2-Qwen2.5-32B-Inst-BaseMerge-TIES-details gated 0 0
460.7 MB
717
0
1.8y
126
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-Slerp-TIES-details gated 0 0
409.2 MB
715
0
2.0y
127
Rachata / qwen35-mature-anger-data 0 0 0
460 KB
708
0
6mo
128
open-llm-leaderboard / zetasepic__Qwen2.5-32B-Instruct-abliterated-v2-details gated 0 0 1
465.3 MB
701
0
1.8y
129
open-llm-leaderboard / yuvraj17__Llama3-8B-abliterated-Spectrum-slerp-details gated 0 0
404.3 MB
699
0
2.1y
130
open-llm-leaderboard / netcat420__MFANN-llama3.1-Abliterated-SLERP-details gated 0 0
409.6 MB
696
0
2.0y
131
open-llm-leaderboard / huihui-ai__Qwen2.5-72B-Instruct-abliterated-details gated 0 0
465.5 MB
694
0
1.8y
132
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-18-ORPO-details gated 0 0
454.4 MB
693
0
2.0y
133
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-24-details gated 0 0
454.4 MB
692
0
2.0y
134
open-llm-leaderboard / netcat420__MFANN-llama3.1-abliterated-v2-details gated 0 0
409.3 MB
690
0
2.0y
135
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-Slerp-V3.2-details gated 0 0
409.4 MB
689
0
2.0y
136
lemon07r / VellumK2-Unfettered-DPO-01 0 0 0 1
16.7 MB
689
5
11mo
137
hotdogs / cyber-sft-agent-qwen38 0 0 0 1
90.3 MB
683
4
2mo
138
cmlzz / details_Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated 0 0 0 1
88.5 MB
681
0
9mo
139
open-llm-leaderboard / CombinHorizon__huihui-ai-abliteratedV2-Qwen2.5-14B-Inst-BaseMerge-TIES-details gated 0 0
460.5 MB
672
0
1.9y
140
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-17-ORPO-alpaca-details gated 0 0
451.1 MB
667
0
2.0y
141
open-llm-leaderboard / T145__ZEUS-8B-V2-abliterated-details gated 0 0
1021.5 MB
667
0
1.8y
142
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-SLERP-TIES-V3-details gated 0 0
409.7 MB
660
0
1.9y
143
open-llm-leaderboard / IlyaGusev__gemma-2-2b-it-abliterated-details gated 0 0
519.6 MB
660
0
1.8y
144
bedderautomation / refusal-geometry-qwen25-3b 0 0 0
350 KB
652
0
7mo
145
EleutherAI / fake-cifar10 0 0 0
151.5 MB
651
0
2.7y
146
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-SLERP-V4-details gated 0 0 1
409.6 MB
647
0
1.9y
147
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-SLERP-TIES-V2-details gated 0 0
409.6 MB
646
0
1.9y
148
GhosTunes / H-to-LLM-BackData 0 0 0
1.7 GB
631
0
21d
149
open-llm-leaderboard / T145__ZEUS-8B-V13-abliterated-details gated 0 0
510.7 MB
630
0
1.8y
150
open-llm-leaderboard / Orion-zhen__phi-4-abliterated-details gated 0 0
404.4 MB
626
0
1.8y
151
open-llm-leaderboard / huihui-ai__Qwen2.5-14B-Instruct-abliterated-v2-details gated 0 0
464.8 MB
620
0
1.9y
152
open-llm-leaderboard / Triangle104__Phi-4-AbliteratedRP-details gated 0 0
406.6 MB
611
0
1.7y
153
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-SLERP-V5-details gated 0 0
409.7 MB
610
0
1.9y
154
open-llm-leaderboard / IlyaGusev__gemma-2-9b-it-abliterated-details gated 0 0
459.5 MB
609
0
1.8y
155
caiovicentino1 / wandering-arc-papers 0 0 0 2
1.3 MB
605
0
4mo
156
open-llm-leaderboard / T145__ZEUS-8B-V17-abliterated-details gated 0 0
512.2 MB
604
0
1.8y
157
open-llm-leaderboard / T145__ZEUS-8B-V17-abliterated-V4-details gated 0 0
510.2 MB
601
0
1.8y
158
open-llm-leaderboard / Undi95__Phi4-abliterated-details gated 0 0
464.4 MB
599
0
1.7y
159
AISafety-Student / labeled-bashBench 0 0 0 1
89.6 MB
598
1
7mo
160
mlx-community / Dolci-Instruct-SFT-No-Tools-100K 0 0 0
99.3 MB
597
1
11mo
161
open-llm-leaderboard / mlx-community__Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float32-details gated 0 0
580.1 MB
585
1
1.8y
162
open-llm-leaderboard / DreadPoor__ZEUS-8B-V17-Abliterated_ALT-details gated 0 0
516.3 MB
585
0
1.8y
163
EleutherAI / fake-cifarnet 0 0 0 1
1.8 GB
582
0
2.7y
164
open-llm-leaderboard / T145__ZEUS-8B-V17-abliterated-V2-details gated 0 0
510.3 MB
581
0
1.8y
165
open-llm-leaderboard / netcat420__Qwen2.5-Coder-Scholar-7B-Abliterated-MFANN-details gated 0 0
465.6 MB
573
0
1.8y
166
open-llm-leaderboard / netcat420__Qwen2.5-Coder-Scholar-7B-Abliterated-MFANN-Slerp-Unretrained-details gated 0 0
465.1 MB
569
0
1.8y
167
open-llm-leaderboard / v000000__L3-8B-Stheno-v3.2-abliterated-details gated 0 0
492.6 MB
563
0
1.8y
168
Butanium / llama-3.1-8b-instruct-assistant-axis 0 0 0
266 KB
549
1
7mo
169
ebowwa / orthogonal-activation-steering-TOXIC 0 0 0
2.1 MB
541
2
2.4y
170
open-llm-leaderboard / huihui-ai__DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-details gated 0 0
451.8 MB
529
0
1.7y
171
mlx-community / Josiefied-Qwen3-dpo-v1-flat 0 0 0 1
1.5 MB
525
2
11mo
172
open-llm-leaderboard / netcat420__MFANN-abliterated-phi2-merge-unretrained-details gated 0 0
462.0 MB
519
0
1.8y
173
open-llm-leaderboard / DavidAU__Qwen2.5-MOE-2X7B-DeepSeek-Abliterated-Censored-19B-details gated 0 0
410.4 MB
499
0
1.6y
174
hotdogs / claude46_filtered 0 0 0
995.7 MB
499
0
5mo
175
open-llm-leaderboard / nbeerbower__EVA-abliterated-TIES-Qwen2.5-1.5B-details gated 0 0
462.3 MB
488
0
1.7y
176
open-llm-leaderboard / failspy__Meta-Llama-3-8B-Instruct-abliterated-v3-details gated 0 0
493.0 MB
486
0
1.7y
177
open-llm-leaderboard / DavidAU__L3.1-MOE-2X8B-Deepseek-DeepHermes-e32-uncensored-abliterated-13.7B-details gated 0 0
411.0 MB
483
0
1.6y
178
open-llm-leaderboard / Nexesenex__pankajmathur_orca_mini_v9_6_1B-instruct-Abliterated-LPL-details gated 0 0
493.9 MB
480
0
1.6y
179
Faruna01 / lsr-anchoring-phase2-results 0 0 0
4.6 MB
480
0
6mo
180
yrdu / S3-CoT-Self-Sampled-Data 0 0 0 1
168.6 MB
473
0
8mo
181
open-llm-leaderboard / nbeerbower__EVA-abliterated-TIES-Qwen2.5-14B-details gated 0 0
459.4 MB
463
0
1.7y
182
open-llm-leaderboard / Nexesenex__Dolphin3.0-Llama3.1-1B-abliterated-details gated 0 0
452.2 MB
456
0
1.6y
183
jvidal / daredevil-abliterated-activations 0 0 0
1.5 GB
452
0
1.2y
184
math-extraction-comp / Undi95__Phi4-abliterated 0 0 0
1.4 MB
450
0
1.7y
185
open-llm-leaderboard / prithivMLmods__Elita-0.1-Distilled-R1-abliterated-details gated 0 0
468.7 MB
423
0
1.7y
186
wangrongsheng / abliterated_dataset 0 0 0 1
1.2 MB
406
0
2.0y
187
snae / emotion_stories_gemma_4_4B 0 0 0
3.2 MB
397
0
3mo
188
hotdogs / cyber-sft-qa-qwen38 0 0 0 1
869.9 MB
392
1
2mo
189
mlx-community / Dolci-Instruct-SFT-No-Tools-400K 0 0 0
391.3 MB
375
1
11mo
190
mlx-community / Dolci-Think-DPO-32B-Flat 0 0 0
1.6 GB
367
2
10mo
191
mild-rgb / em-exp3-activations 0 0 0
3.3 GB
364
0
3mo
192
DmitryDB / Qwen3.6-35B-A3B-heretic-study 0 0 0 1
737.6 MB
341
0
2mo
193
math-extraction-comp / byroneverson__Yi-1.5-9B-Chat-16K-abliterated 0 0 0
1.2 MB
338
0
1.8y
194
anon-lsr-2026 / lsr-anchoring-results 0 0 0
2.0 MB
331
0
5mo
195
Butanium / qwen-2.5-7b-instruct-assistant-axis 0 0 0
205 KB
317
0
7mo
196
caiovicentino1 / openinterp-paper-mega-conditionally-causal 0 0 0
12.6 MB
301
0
5mo
197
ShantanuT01 / R255-Finetuning-Datasets 0 0 0
11.9 MB
294
0
1.6y
198
Panminghui / safekeep-paired-data 0 0 0 1
7.1 MB
290
1
2mo
199
1mleb / context-tampering-v1 0 0 0
21.6 GB
289
0
4mo
200
mlx-community / Dolci-Instruct-SFT-No-Tools-200K 0 0 0
196.8 MB
288
1
11mo
201
math-extraction-comp / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v2 0 0 0
1.5 MB
286
0
1.8y
202
math-extraction-comp / mlx-community__Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float32 0 0 0
1.3 MB
283
1
1.8y
203
math-extraction-comp / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v3 0 0 0
1.5 MB
282
0
1.8y
204
puwaer / cvalues_rlhf_jp_cot 0 0 0 1
487.3 MB
281
0
9mo
205
brikdavies / msm-graded-rollouts 0 0 0 1
212.4 MB
275
0
4mo
206
multilingual-safety-anon / lsr-anchoring-phase2-results 0 0 0
4.6 MB
274
0
3mo
207
puwaer / cvalues_rlhf_en 0 0 0
166.9 MB
273
1
11mo
208
yelyzavetahusieva / geometry-of-harmfulness-in-multi-turn-attacks 0 0 0 1
1.7 GB
273
0
3mo
209
math-extraction-comp / IlyaGusev__gemma-2-9b-it-abliterated 0 0 0
1.3 MB
272
0
1.8y
210
swzzzzc / Anti-Sycophancy-RepE-384 0 0 0 1
245 KB
272
0
8mo
211
math-extraction-comp / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1 0 0 0
1.6 MB
271
0
1.8y
212
zachperlman20 / meta-token-gen-steer-cache 0 0 0
950.3 MB
266
0
1mo
213
math-extraction-comp / IlyaGusev__gemma-2-2b-it-abliterated 0 0 0
1.3 MB
263
0
1.8y
214
HoangCuongNguyen / refusal-direction-results 0 0 0
10.9 MB
263
0
5mo
215
math-extraction-comp / Goekdeniz-Guelmez__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 0 0 0
1.6 MB
258
0
1.8y
216
DeepRCL / SteeringGeometry 0 0 0 2
12.9 MB
258
0
1mo
217
ghost-actual / OpenHermes-NoRefusal-95K 0 0 0 1
143.3 MB
257
1
1mo
218
sterlixlol / kazi-agentic-traces-19k 0 0 0 1
340.9 MB
254
2
5mo
219
Butanium / gemma-3-4b-it-assistant-axis 0 0 0
180 KB
248
0
7mo
220
OALL / details_zetasepic__Qwen2.5-32B-Instruct-abliterated-v2_v2_alrage 0 0 0
17.5 MB
247
0
1.6y
221
puwaer / cvalues_rlhf_jp 0 0 0
212.3 MB
242
0
11mo
222
OALL / details_huihui-ai__DeepSeek-R1-Distill-Qwen-14B-abliterated-v2 0 0 0
1.3 MB
236
0
1.7y
223
AlexWortega / capability-vectors 0 0 0 1
3.4 MB
235
0
4mo
224
mayank-dubey-ai / sdxl-activation-steering 0 0 0 1
11.8 MB
229
0
1mo
225
AfkaraLP / racist-and-sex-jokes-enhanced 0 0 0 1
1019 KB
227
1
5mo
226
PhillipsLab / conciseness_verbosity_contrast 0 0 0 1
431 KB
223
1
11mo
227
assisted-diffusion / em-activation-transport 0 0 0 1
3.1 GB
223
0
2mo
228
shehryars715 / tone-slider 0 0 0 1
1.6 MB
219
0
1mo
229
hotdogs / sme-sft-docdata-qwen38 0 0 0 1
45.6 MB
215
0
2mo
230
Quinn67 / ShrimpMoss_Chinese_Censorship_Abliteration 0 0 0
54.1 MB
210
0
1mo
231
jhk0317 / qwen3.8-27b-refusal-ablation-artifacts 0 0 0
31.5 MB
210
0
24d
232
Rootkit7 / pentest-redteam-steering 0 0 0
1.3 MB
209
0
6mo
233
RumiaChannel / harmless_behaviors_ja_synth 0 0 0
291 KB
207
0
5mo
234
flas-ai / flas-concept-46k 0 0 0 1
845.6 MB
206
1
4mo
235
hotdogs / thinkingcap-sft-qwen38-27b 0 0 0
885 KB
205
2
1mo
236
DuoNeural / Gemma4-E2B-SFT-CoT 0 0 0
6.4 MB
204
0
5mo
237
snae / emotion_stories_Apertus_8B_Instruct 0 0 0 1
4.1 MB
201
0
3mo
238
BIGJUTT / abliterix-datasets 0 0 0 1
1.9 MB
200
1
4mo
239
puwaer / cvalues_rlhf_zh_cot 0 0 0
214.5 MB
199
1
9mo
240
anicka / guppylm-dual-denial-data 0 0 0 1
7.3 MB
197
0
5mo
241
PersonaBias / alpha_beta_intervention 0 0 0 1
2.7 MB
196
0
1mo
242
ncrispino / tool-call-steering-data 0 0 0
16.0 MB
195
0
10mo
243
B2J / latent-state-tracking-minicpm5 0 0 0
487 KB
193
0
1mo
244
mild-rgb / indy-mech-extension-qwen3-8b-persona-probes 0 0 0
13.4 GB
179
0
1mo
245
abliterationaiorg / fictional-clinical-pii-governance 0 0 0 1
23 KB
172
0
5mo
246
puwaer / cvalues_rlhf_en_cot 0 0 0
427.7 MB
171
0
9mo
247
abliterationaiorg / trust-safety-action-routing 0 0 0
23 KB
169
1
5mo
248
xzAscC / TDNV-results 0 0 0
40.2 MB
169
0
14d
249
abliterationai / fictional-clinical-pii-governance 0 0 0
23 KB
167
0
5mo
250
AtomicChat / Ternary-Bonsai-2-27B-Uncensored-LoRA-GGUF-metrics 0 just added 0
17 KB
161
0
28d
251
RadicalNotionAI / modelatlas-community 0 0 0
7 KB
159
0
6mo
252
hirundo-io / refinement-abliterated-thinking_heretic_short_answers 0 0 0 1
2.4 MB
158
1
4mo
253
ArthT / abuse-revenge-pilot 0 just added 0 1
679.9 MB
157
0
7d
254
dec0dedd / abliterated-Llama-3.1-8B-responses 0 0 0 1
756 KB
154
0
5mo
255
maximuspowers / representation-engineering-results 0 0 0 1
543 KB
146
0
10mo
256
finnianx / gemma-abliterated-distill 0 0 0 1
25.7 MB
146
0
5mo
257
Sumit7194 / phronesis-fm-x 0 0 0
802 KB
144
1
4mo
258
LieUr / qwen2.5-1.5b_gsm8k_repairdeltas 0 0 0
9.1 MB
139
0
3mo
259
XuehangCang / unsafe_qa 0 0 0 1
5.9 MB
138
0
4mo
260
wassname / abliterated-llama-known-prompts 0 0 0
2 KB
137
0
2.4y
261
Drishti / emotion-vector-robustness-audit 0 0 0 1
7.4 MB
135
0
3mo
262
Aipotek / steer-cards-gemma3 0 0 0 1
71.8 MB
134
0
16d
263
dec0dedd / abliterated-gpt-oss-20b-responses 0 0 0 1
2.0 MB
133
1
5mo
264
professorsynapse / eh-probe-directions 0 0 0
106 KB
133
0
3mo
265
strangerguardhf / Caption3o-Opt-Abliterated-5K gated 0 0
651.3 MB
131
2
1.2y
266
rx1lora / tb00-VellumK2-Unfettered-DPO-01 0 0 0
16.7 MB
125
1
2mo
267
CapyStudios / Capy-CrackV2 0 0 0
1.6 MB
120
0
5mo
268
strangecreator / detailed-vs-vague-pairs-english 0 0 0
544 KB
120
0
10d
269
natong19 / china_qa_preferences 0 0 0
14.0 MB
119
1
10mo
270
SubliminalMisalignment / abliterated-distill-30k 0 0 0 1
23.4 MB
119
1
10mo
271
abliterationai / trust-safety-action-routing 0 0 0
23 KB
118
0
5mo
272
wisent-ai / uncensorbench-leaderboard 0 0 0 1
4 KB
117
0
10mo
273
sinhal / Charcard-Roleplay-ShareGPT-NSFW 0 0 0
164.7 MB
117
0
2mo
274
SubliminalMisalignment / abliterated-distill-15k 0 0 0 1
11.4 MB
115
0
10mo
275
natong19 / toxic_qa_preferences 0 0 0
13.0 MB
110
0
10mo
276
oyi77 / synthetic-dataset-factory 0 0 0
4 KB
98
0
7mo
277
daway845 / Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated 0 0 0
22.3 GB
98
0
4mo
278
knoveleng / stylegen 0 0 0
973 KB
98
0
1mo
279
chibifire / harmless-prompts-en-train 0 0 0 1
1.2 MB
96
0
1mo
280
sbussiso / qwen2.5-7b-abliterated-evidence 0 0 0
8.8 MB
92
0
22d
281
dec0dedd / abliterated-qwen3-4b-instruct-2507-responses 0 0 0 1
858 KB
90
0
5mo
282
abhisheksharma0994 / apple-m5-pro-24gb-llm-tps-benchmarks 0 0 0 1
14 KB
87
0
1mo
283
alperiox / arithmetic-abliteration-results 0 0 0
245 KB
84
0
6mo
284
hirundo-io / abliteration-harmful-enriched-categorized 0 0 0
486 KB
84
0
3mo
285
KorolOrol / gpt2-steering-repair-results 0 0 0
27.8 MB
81
0
1mo
286
AtomicChat / Ternary-Bonsai-2-9B-Uncensored-LoRA-GGUF-metrics 0 just added 0
15 KB
74
0
6d
287
AtomicChat / Ternary-Bonsai-2-2B-Uncensored-LoRA-GGUF-metrics 0 just added 0
13 KB
73
0
6d
288
AtomicChat / Ternary-Bonsai-2-4B-Uncensored-LoRA-GGUF-metrics 0 just added 0
15 KB
71
0
6d
289
gustavecortal / cognitive-reframing-pairs 0 just added 0 1
3.2 MB
70
1
3d
290
TrustMI / trustmi-conversations 0 0 0
65.7 MB
70
0
12d
291
jcksanderson / obliteratus-harmless 0 0 0
39 KB
69
0
2mo
292
jcksanderson / obliteratus-harmful 0 0 0 1
38 KB
67
0
2mo
293
zzzkshero / abliterated 0 0 0
7.6 GB
62
0
5mo
294
labrecque83 / abliterated-distill-15k 0 0 0 1
11.4 MB
61
0
1mo
295
CounterSteer / sycophancy-data 0 0 0
103.5 MB
60
0
1mo
296
CademAI / temp-deepseek-v4-flash-abliterated 0 0 0
156.9 GB
55
0
2mo
297
strangecreator / harmful-requests-english 0 0 0
230 KB
54
0
10d
298
AlexWortega / answers gated 0 0
58.6 MB
52
0
5mo
299
arjhinety / small-mind-probe-sets 0 0 0
29 KB
51
0
1mo
300
DragonForgeStudios / forge-games 0 0 0
165.2 MB
51
0
1mo
301
darkengross / abliteration-qwen25-7b-safety-audit 0 0 0 1
20.3 MB
46
0
1mo
302
LeoRodrigues05 / safety-cot-interventions-v5 gated 0 0
5.8 GB
41
1
3mo
303
ElementMerc / senbonzakura-dataset gated 0 0 1
707 KB
29
0
2mo
001
gustavecortal / cognitive-reframing-pairs 0 just added 0 1
3.2 MB
70
1
3d
002
AtomicChat / Ternary-Bonsai-2-9B-Uncensored-LoRA-GGUF-metrics 0 just added 0
15 KB
74
0
6d
003
AtomicChat / Ternary-Bonsai-2-4B-Uncensored-LoRA-GGUF-metrics 0 just added 0
15 KB
71
0
6d
004
AtomicChat / Ternary-Bonsai-2-2B-Uncensored-LoRA-GGUF-metrics 0 just added 0
13 KB
73
0
6d
005
ArthT / abuse-revenge-pilot 0 just added 0 1
679.9 MB
157
0
7d
006
sunnycloudhust / CHaRS-activations 0 just added 0
63.8 GB
5.3k
2
8d
007
strangecreator / harmful-requests-english 0 0 0
230 KB
54
0
10d
008
stablellama / erotic-confident-woman-prompts 0 0 0
12.6 MB
917
2
10d
009
strangecreator / detailed-vs-vague-pairs-english 0 0 0
544 KB
120
0
10d
010
TrustMI / trustmi-conversations 0 0 0
65.7 MB
70
0
12d
011
xzAscC / TDNV-results 0 0 0
40.2 MB
169
0
14d
012
Aipotek / steer-cards-gemma3 0 0 0 1
71.8 MB
134
0
16d
013
GhosTunes / H-to-LLM-BackData 0 0 0
1.7 GB
631
0
21d
014
sbussiso / qwen2.5-7b-abliterated-evidence 0 0 0
8.8 MB
92
0
22d
015
jhk0317 / qwen3.8-27b-refusal-ablation-artifacts 0 0 0
31.5 MB
210
0
24d
016
AtomicChat / Ternary-Bonsai-2-27B-Uncensored-LoRA-GGUF-metrics 0 just added 0
17 KB
161
0
28d
017
XoxoMerlin / erotic-image-prompts 0 0 0
104.7 MB
3.2k
0
28d
018
junvin / erotic-image-prompts 0 0 0
104.7 MB
3.2k
0
29d
019
stablellama / erotic-image-prompts 0 0 0
104.7 MB
11.9k
66
1mo
020
knoveleng / stylegen 0 0 0
973 KB
98
0
1mo
021
mild-rgb / ouro-1.4b-thinking-evals 0 0 0
2.1 GB
1.9k
1
1mo
022
B2J / latent-state-tracking-minicpm5 0 0 0
487 KB
193
0
1mo
023
CounterSteer / sycophancy-data 0 0 0
103.5 MB
60
0
1mo
024
PersonaBias / alpha_beta_intervention 0 0 0 1
2.7 MB
196
0
1mo
025
DragonForgeStudios / forge-games 0 0 0
165.2 MB
51
0
1mo
026
darkengross / abliteration-qwen25-7b-safety-audit 0 0 0 1
20.3 MB
46
0
1mo
027
labrecque83 / abliterated-distill-15k 0 0 0 1
11.4 MB
61
0
1mo
028
arjhinety / small-mind-probe-sets 0 0 0
29 KB
51
0
1mo
029
zachperlman20 / meta-token-gen-steer-cache 0 0 0
950.3 MB
266
0
1mo
030
shehryars715 / tone-slider 0 0 0 1
1.6 MB
219
0
1mo
031
mild-rgb / indy-mech-extension-qwen3-8b-persona-probes 0 0 0
13.4 GB
179
0
1mo
032
DeepRCL / SteeringGeometry 0 0 0 2
12.9 MB
258
0
1mo
033
chibifire / harmless-prompts-en-train 0 0 0 1
1.2 MB
96
0
1mo
034
ghost-actual / OpenHermes-NoRefusal-95K 0 0 0 1
143.3 MB
257
1
1mo
035
Quinn67 / ShrimpMoss_Chinese_Censorship_Abliteration 0 0 0
54.1 MB
210
0
1mo
036
mayank-dubey-ai / retro-icon-rl 0 0 0
637.1 MB
1.3k
0
1mo
037
mayank-dubey-ai / sdxl-activation-steering 0 0 0 1
11.8 MB
229
0
1mo
038
hotdogs / thinkingcap-sft-qwen38-27b 0 0 0
885 KB
205
2
1mo
039
abhisheksharma0994 / apple-m5-pro-24gb-llm-tps-benchmarks 0 0 0 1
14 KB
87
0
1mo
040
mayank-dubey-ai / enterprise-100-db-steering 0 0 0
2.2 MB
930
1
1mo
041
KorolOrol / gpt2-steering-repair-results 0 0 0
27.8 MB
81
0
1mo
042
hotdogs / sme-sft-docdata-qwen38 0 0 0 1
45.6 MB
215
0
2mo
043
sinhal / Charcard-Roleplay-ShareGPT-NSFW 0 0 0
164.7 MB
117
0
2mo
044
hotdogs / cyber-sft-agent-qwen38 0 0 0 1
90.3 MB
683
4
2mo
045
rx1lora / tb00-VellumK2-Unfettered-DPO-01 0 0 0
16.7 MB
125
1
2mo
046
dementor-research / dementor-complete-experiment-results 0 0 0
8.2 GB
5.1k
0
2mo
047
hotdogs / cyber-sft-qa-qwen38 0 0 0 1
869.9 MB
392
1
2mo
048
jcksanderson / obliteratus-harmless 0 0 0
39 KB
69
0
2mo
049
jcksanderson / obliteratus-harmful 0 0 0 1
38 KB
67
0
2mo
050
CademAI / temp-deepseek-v4-flash-abliterated 0 0 0
156.9 GB
55
0
2mo
051
ElementMerc / senbonzakura-dataset gated 0 0 1
707 KB
29
0
2mo
052
assisted-diffusion / em-activation-transport 0 0 0 1
3.1 GB
223
0
2mo
053
Panminghui / safekeep-paired-data 0 0 0 1
7.1 MB
290
1
2mo
054
amildravid4292 / reason-math-correctness 0 0 0 1
61.0 GB
727
0
2mo
055
DmitryDB / Qwen3.6-35B-A3B-heretic-study 0 0 0 1
737.6 MB
341
0
2mo
056
musicakamusic / crimsonred-paper-replication 0 0 0 1
29.8 MB
741
0
2mo
057
hirundo-io / abliteration-harmful-enriched-categorized 0 0 0
486 KB
84
0
3mo
058
mild-rgb / em-exp3-activations 0 0 0
3.3 GB
364
0
3mo
059
Drishti / emotion-vector-robustness-audit 0 0 0 1
7.4 MB
135
0
3mo
060
yelyzavetahusieva / geometry-of-harmfulness-in-multi-turn-attacks 0 0 0 1
1.7 GB
273
0
3mo
061
multilingual-safety-anon / lsr-anchoring-phase2-results 0 0 0
4.6 MB
274
0
3mo
062
LeoRodrigues05 / safety-cot-interventions-v5 gated 0 0
5.8 GB
41
1
3mo
063
LieUr / qwen2.5-1.5b_gsm8k_repairdeltas 0 0 0
9.1 MB
139
0
3mo
064
professorsynapse / eh-probe-directions 0 0 0
106 KB
133
0
3mo
065
snae / emotion_stories_gemma_4_4B 0 0 0
3.2 MB
397
0
3mo
066
snae / emotion_stories_Apertus_8B_Instruct 0 0 0 1
4.1 MB
201
0
3mo
067
GrantAE / ukaisi-esr-phase-1 0 0 0 1
767.6 MB
805
0
4mo
068
daway845 / Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated 0 0 0
22.3 GB
98
0
4mo
069
wassname / moral_stories_foundations 0 0 0 1
5.2 MB
894
0
4mo
070
XuehangCang / unsafe_qa 0 0 0 1
5.9 MB
138
0
4mo
071
future-probes / activation_steering 0 0 0
5.0 GB
2.0k
0
4mo
072
brikdavies / msm-graded-rollouts 0 0 0 1
212.4 MB
275
0
4mo
073
1mleb / context-tampering-v1 0 0 0
21.6 GB
289
0
4mo
074
BIGJUTT / abliterix-datasets 0 0 0 1
1.9 MB
200
1
4mo
075
hirundo-io / refinement-abliterated-thinking_heretic_short_answers 0 0 0 1
2.4 MB
158
1
4mo
076
Sumit7194 / phronesis-fm-x 0 0 0
802 KB
144
1
4mo
077
dungnv / assistant-axis-qwen-3-14b 0 0 0 1
114.8 MB
1.1k
0
4mo
078
flas-ai / flas-concept-46k 0 0 0 1
845.6 MB
206
1
4mo
079
caiovicentino1 / wandering-arc-papers 0 0 0 2
1.3 MB
605
0
4mo
080
AlexWortega / capability-vectors 0 0 0 1
3.4 MB
235
0
4mo
081
memo-ozdincer / jepa-qwen3-32b-ce-cb-pra-2026-05-20 0 0 0 1
758.5 MB
4.1k
0
5mo
082
pandaman007 / steered-persona-space 0 0 0
539.6 MB
9.1k
0
5mo
083
caiovicentino1 / openinterp-paper-mega-conditionally-causal 0 0 0
12.6 MB
301
0
5mo
084
iNLP-Lab / multilingual-safety 0 0 0
6.8 MB
966
0
5mo
085
dec0dedd / abliterated-Llama-3.1-8B-responses 0 0 0 1
756 KB
154
0
5mo
086
AlexWortega / answers gated 0 0
58.6 MB
52
0
5mo
087
finnianx / gemma-abliterated-distill 0 0 0 1
25.7 MB
146
0
5mo
088
abliterationaiorg / trust-safety-action-routing 0 0 0
23 KB
169
1
5mo
089
abliterationaiorg / fictional-clinical-pii-governance 0 0 0 1
23 KB
172
0
5mo
090
abliterationai / trust-safety-action-routing 0 0 0
23 KB
118
0
5mo
091
abliterationai / fictional-clinical-pii-governance 0 0 0
23 KB
167
0
5mo
092
dec0dedd / abliterated-gpt-oss-20b-responses 0 0 0 1
2.0 MB
133
1
5mo
093
sterlixlol / kazi-agentic-traces-19k 0 0 0 1
340.9 MB
254
2
5mo
094
nips234678 / poolbench-activations 0 0 0
860.6 GB
3.3k
0
5mo
095
alliedtoasters / forbidden-backrooms-gemma-4-31B-it 0 0 0 1
315.2 MB
2.4k
0
5mo
096
RumiaChannel / harmless_behaviors_ja_synth 0 0 0
291 KB
207
0
5mo
097
DuoNeural / Gemma4-E2B-SFT-CoT 0 0 0
6.4 MB
204
0
5mo
098
dec0dedd / abliterated-qwen3-4b-instruct-2507-responses 0 0 0 1
858 KB
90
0
5mo
099
cyu96374 / MFT-LLM-binding-axis-multimodel-2026-05 0 0 0
7.9 GB
1.5k
0
5mo
100
hotdogs / claude46_filtered 0 0 0
995.7 MB
499
0
5mo
101
AfkaraLP / racist-and-sex-jokes-enhanced 0 0 0 1
1019 KB
227
1
5mo
102
anon-lsr-2026 / lsr-anchoring-results 0 0 0
2.0 MB
331
0
5mo
103
anicka / guppylm-dual-denial-data 0 0 0 1
7.3 MB
197
0
5mo
104
HoangCuongNguyen / refusal-direction-results 0 0 0
10.9 MB
263
0
5mo
105
CapyStudios / Capy-CrackV2 0 0 0
1.6 MB
120
0
5mo
106
zzzkshero / abliterated 0 0 0
7.6 GB
62
0
5mo
107
alperiox / arithmetic-abliteration-results 0 0 0
245 KB
84
0
6mo
108
pandaman007 / assistant-axis-abliteration-vectors 0 0 0
24.5 GB
9.5k
0
6mo
109
xiachongfeng / persona 0 0 0 1
289.0 MB
2.1k
0
6mo
110
Rachata / qwen35-mature-anger-data 0 0 0
460 KB
708
0
6mo
111
cudabenchmarktest / r9-research-framework 0 0 0 1
1.5 MB
939
0
6mo
112
Rootkit7 / pentest-redteam-steering 0 0 0
1.3 MB
209
0
6mo
113
Faruna01 / lsr-anchoring-phase2-results 0 0 0
4.6 MB
480
0
6mo
114
RadicalNotionAI / modelatlas-community 0 0 0
7 KB
159
0
6mo
115
oyi77 / synthetic-dataset-factory 0 0 0
4 KB
98
0
7mo
116
daway845 / huihui1.4.19_public 0 0 0
16.2 GB
1.7k
0
7mo
117
AISafety-Student / labeled-bashBench 0 0 0 1
89.6 MB
598
1
7mo
118
daway845 / huihui1.4.12_public 0 0 0
13.2 GB
1.4k
0
7mo
119
daway845 / huihui1.4.11_public 0 0 0
13.2 GB
1.4k
0
7mo
120
daway845 / huihui1.4.10_public 0 0 0
10.1 GB
1.1k
0
7mo
121
daway845 / huihui1.4.6_public 0 0 0
17.7 GB
2.0k
0
7mo
122
bedderautomation / refusal-geometry-qwen25-3b 0 0 0
350 KB
652
0
7mo
123
Butanium / gemma-3-4b-it-assistant-axis 0 0 0
180 KB
248
0
7mo
124
Butanium / llama-3.1-8b-instruct-assistant-axis 0 0 0
266 KB
549
1
7mo
125
Butanium / qwen-2.5-7b-instruct-assistant-axis 0 0 0
205 KB
317
0
7mo
126
Ishaank18 / visual-refusal-gap 0 0 0
467.4 MB
1.3k
0
7mo
127
swzzzzc / Anti-Sycophancy-RepE-384 0 0 0 1
245 KB
272
0
8mo
128
yrdu / S3-CoT-Self-Sampled-Data 0 0 0 1
168.6 MB
473
0
8mo
129
massines3a / assistant-axis-vectors 0 0 0 1
176.7 MB
1.0k
0
8mo
130
cmlzz / details_Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated 0 0 0 1
88.5 MB
681
0
9mo
131
lu-christina / assistant-axis-vectors 0 0 0 1
1.2 GB
14.4k
13
9mo
132
puwaer / cvalues_rlhf_zh_cot 0 0 0
214.5 MB
199
1
9mo
133
puwaer / cvalues_rlhf_jp_cot 0 0 0 1
487.3 MB
281
0
9mo
134
puwaer / cvalues_rlhf_en_cot 0 0 0
427.7 MB
171
0
9mo
135
mlx-community / Dolci-Think-DPO-32B-Flat 0 0 0
1.6 GB
367
2
10mo
136
SubliminalMisalignment / abliterated-distill-30k 0 0 0 1
23.4 MB
119
1
10mo
137
SubliminalMisalignment / abliterated-distill-15k 0 0 0 1
11.4 MB
115
0
10mo
138
maximuspowers / representation-engineering-results 0 0 0 1
543 KB
146
0
10mo
139
ncrispino / tool-call-steering-data 0 0 0
16.0 MB
195
0
10mo
140
wisent-ai / uncensorbench-leaderboard 0 0 0 1
4 KB
117
0
10mo
141
natong19 / china_qa_preferences 0 0 0
14.0 MB
119
1
10mo
142
natong19 / toxic_qa_preferences 0 0 0
13.0 MB
110
0
10mo
143
mlx-community / Dolci-Instruct-SFT-No-Tools-400K 0 0 0
391.3 MB
375
1
11mo
144
mlx-community / Dolci-Instruct-SFT-No-Tools-200K 0 0 0
196.8 MB
288
1
11mo
145
mlx-community / Dolci-Instruct-SFT-No-Tools-100K 0 0 0
99.3 MB
597
1
11mo
146
puwaer / cvalues_rlhf_jp 0 0 0
212.3 MB
242
0
11mo
147
puwaer / cvalues_rlhf_en 0 0 0
166.9 MB
273
1
11mo
148
lemon07r / VellumK2-Unfettered-DPO-01 0 0 0 1
16.7 MB
689
5
11mo
149
mlx-community / Josiefied-Qwen3-dpo-v1-flat 0 0 0 1
1.5 MB
525
2
11mo
150
PhillipsLab / conciseness_verbosity_contrast 0 0 0 1
431 KB
223
1
11mo
151
jvidal / daredevil-abliterated-activations 0 0 0
1.5 GB
452
0
1.2y
152
strangerguardhf / Caption3o-Opt-Abliterated-5K gated 0 0
651.3 MB
131
2
1.2y
153
lasrprobegen / refusal-activations 0 0 0 1
1.21 TB
74.6k
1
1.2y
154
mlx-community / hermes-3 0 0 0 1
772.5 MB
1.3k
6
1.3y
155
mlx-community / gsm8k 0 0 0 1
3.7 MB
1.4k
2
1.3y
156
magiccodingman / QwQ-32B-abliterated-131k-GGUF-Yarn-Imatrix 0 0 0
127.3 GB
2.8k
17
1.4y
157
QuixiAI / china-refusals 0 0 0 1
1.5 MB
2.3k
53
1.4y
158
ShantanuT01 / R255-Finetuning-Datasets 0 0 0
11.9 MB
294
0
1.6y
159
open-llm-leaderboard / DavidAU__Qwen2.5-MOE-2X7B-DeepSeek-Abliterated-Censored-19B-details gated 0 0
410.4 MB
499
0
1.6y
160
open-llm-leaderboard / DavidAU__L3.1-MOE-2X8B-Deepseek-DeepHermes-e32-uncensored-abliterated-13.7B-details gated 0 0
411.0 MB
483
0
1.6y
161
OALL / details_zetasepic__Qwen2.5-32B-Instruct-abliterated-v2_v2 0 0 0 1
202.7 MB
1.2k
0
1.6y
162
OALL / details_zetasepic__Qwen2.5-32B-Instruct-abliterated-v2_v2_alrage 0 0 0
17.5 MB
247
0
1.6y
163
open-llm-leaderboard / Nexesenex__pankajmathur_orca_mini_v9_6_1B-instruct-Abliterated-LPL-details gated 0 0
493.9 MB
480
0
1.6y
164
open-llm-leaderboard / Nexesenex__Dolphin3.0-Llama3.1-1B-abliterated-details gated 0 0
452.2 MB
456
0
1.6y
165
open-llm-leaderboard / failspy__Meta-Llama-3-8B-Instruct-abliterated-v3-details gated 0 0
493.0 MB
486
0
1.7y
166
HarethahMo / extended-refusal 0 0 0 1
12.8 MB
979
1
1.7y
167
open-llm-leaderboard / nbeerbower__EVA-abliterated-TIES-Qwen2.5-14B-details gated 0 0
459.4 MB
463
0
1.7y
168
open-llm-leaderboard / prithivMLmods__Elita-0.1-Distilled-R1-abliterated-details gated 0 0
468.7 MB
423
0
1.7y
169
OALL / details_huihui-ai__DeepSeek-R1-Distill-Qwen-32B-abliterated 0 0 0
85.5 MB
879
0
1.7y
170
open-llm-leaderboard / nbeerbower__EVA-abliterated-TIES-Qwen2.5-1.5B-details gated 0 0
462.3 MB
488
0
1.7y
171
OALL / details_huihui-ai__DeepSeek-R1-Distill-Qwen-14B-abliterated-v2 0 0 0
1.3 MB
236
0
1.7y
172
open-llm-leaderboard / huihui-ai__DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-details gated 0 0
451.8 MB
529
0
1.7y
173
open-llm-leaderboard / Triangle104__Phi-4-AbliteratedRP-details gated 0 0
406.6 MB
611
0
1.7y
174
math-extraction-comp / Undi95__Phi4-abliterated 0 0 0
1.4 MB
450
0
1.7y
175
Nafnlaus / ShrimpMoss_Chinese_Censorship_Abliteration 0 0 0 2
54.1 MB
5.0k
8
1.7y
176
open-llm-leaderboard / Undi95__Phi4-abliterated-details gated 0 0
464.4 MB
599
0
1.7y
177
OALL / details_byroneverson__Yi-1.5-34B-Chat-abliterated 0 0 0
107.1 MB
1.1k
0
1.7y
178
OALL / details_zetasepic__Qwen2.5-72B-Instruct-abliterated 0 0 0 1
87.2 MB
1.0k
0
1.7y
179
open-llm-leaderboard / netcat420__Qwen2.5-Coder-Scholar-7B-Abliterated-MFANN-Slerp-Unretrained-details gated 0 0
465.1 MB
569
0
1.8y
180
open-llm-leaderboard / DreadPoor__ZEUS-8B-V17-Abliterated_ALT-details gated 0 0
516.3 MB
585
0
1.8y
181
open-llm-leaderboard / huihui-ai__Qwen2.5-72B-Instruct-abliterated-details gated 0 0
465.5 MB
694
0
1.8y
182
open-llm-leaderboard / netcat420__MFANN-abliterated-phi2-merge-unretrained-details gated 0 0
462.0 MB
519
0
1.8y
183
math-extraction-comp / mlx-community__Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float32 0 0 0
1.3 MB
283
1
1.8y
184
math-extraction-comp / IlyaGusev__gemma-2-9b-it-abliterated 0 0 0
1.3 MB
272
0
1.8y
185
math-extraction-comp / IlyaGusev__gemma-2-2b-it-abliterated 0 0 0
1.3 MB
263
0
1.8y
186
math-extraction-comp / byroneverson__Yi-1.5-9B-Chat-16K-abliterated 0 0 0
1.2 MB
338
0
1.8y
187
open-llm-leaderboard / zetasepic__Qwen2.5-32B-Instruct-abliterated-v2-details gated 0 0 1
465.3 MB
701
0
1.8y
188
open-llm-leaderboard / mlx-community__Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float32-details gated 0 0
580.1 MB
585
1
1.8y
189
open-llm-leaderboard / IlyaGusev__gemma-2-9b-it-abliterated-details gated 0 0
459.5 MB
609
0
1.8y
190
open-llm-leaderboard / v000000__L3-8B-Stheno-v3.2-abliterated-details gated 0 0
492.6 MB
563
0
1.8y
191
math-extraction-comp / Goekdeniz-Guelmez__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 0 0 0
1.6 MB
258
0
1.8y
192
math-extraction-comp / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v3 0 0 0
1.5 MB
282
0
1.8y
193
math-extraction-comp / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v2 0 0 0
1.5 MB
286
0
1.8y
194
math-extraction-comp / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1 0 0 0
1.6 MB
271
0
1.8y
195
open-llm-leaderboard / IlyaGusev__gemma-2-2b-it-abliterated-details gated 0 0
519.6 MB
660
0
1.8y
196
open-llm-leaderboard / T145__ZEUS-8B-V17-abliterated-V4-details gated 0 0
510.2 MB
601
0
1.8y
197
open-llm-leaderboard / T145__ZEUS-8B-V17-abliterated-V2-details gated 0 0
510.3 MB
581
0
1.8y
198
open-llm-leaderboard / T145__ZEUS-8B-V17-abliterated-details gated 0 0
512.2 MB
604
0
1.8y
199
open-llm-leaderboard / netcat420__Qwen2.5-Coder-Scholar-7B-Abliterated-MFANN-details gated 0 0
465.6 MB
573
0
1.8y
200
open-llm-leaderboard / T145__ZEUS-8B-V13-abliterated-details gated 0 0
510.7 MB
630
0
1.8y
201
open-llm-leaderboard / T145__ZEUS-8B-V2-abliterated-details gated 0 0
1021.5 MB
667
0
1.8y
202
open-llm-leaderboard / CombinHorizon__zetasepic-abliteratedV2-Qwen2.5-32B-Inst-BaseMerge-TIES-details gated 0 0
460.7 MB
717
0
1.8y
203
open-llm-leaderboard / Orion-zhen__phi-4-abliterated-details gated 0 0
404.4 MB
626
0
1.8y
204
open-llm-leaderboard / CombinHorizon__huihui-ai-abliterated-Qwen2.5-32B-Inst-BaseMerge-TIES-details gated 0 0
460.4 MB
797
0
1.9y
205
open-llm-leaderboard / CombinHorizon__huihui-ai-abliteratedV2-Qwen2.5-14B-Inst-BaseMerge-TIES-details gated 0 0
460.5 MB
672
0
1.9y
206
open-llm-leaderboard / huihui-ai__Qwen2.5-14B-Instruct-abliterated-v2-details gated 0 0
464.8 MB
620
0
1.9y
207
open-llm-leaderboard / CombinHorizon__Josiefied-abliteratedV4-Qwen2.5-14B-Inst-BaseMerge-TIES-details gated 0 0
460.4 MB
739
0
1.9y
208
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-SLERP-TIES-V3-details gated 0 0
409.7 MB
660
0
1.9y
209
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-SLERP-V5-details gated 0 0
409.7 MB
610
0
1.9y
210
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-details gated 0 0
1.1 GB
808
0
1.9y
211
open-llm-leaderboard / zetasepic__Qwen2.5-72B-Instruct-abliterated-details gated 0 0 1
409.9 MB
765
0
1.9y
212
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-SLERP-V4-details gated 0 0 1
409.6 MB
647
0
1.9y
213
lenML / abliterate-refusal-cn 0 0 0 1
5.0 MB
743
0
1.9y
214
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-SLERP-TIES-V2-details gated 0 0
409.6 MB
646
0
1.9y
215
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-17-18-24-details gated 0 0
908.3 MB
762
0
2.0y
216
open-llm-leaderboard / ymcki__gemma-2-2b-ORPO-jpn-it-abliterated-18-details gated 0 0 1
2.3 GB
868
0
2.0y
217
open-llm-leaderboard / ymcki__gemma-2-2b-ORPO-jpn-it-abliterated-18-merge-details gated 0 0 1
1.8 GB
987
0
2.0y
218
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-Slerp-V3.2-details gated 0 0
409.4 MB
689
0
2.0y
219
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-Slerp-TIES-details gated 0 0
409.2 MB
715
0
2.0y
220
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-details gated 0 0
553.9 MB
816
0
2.0y
221
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-17-ORPO-alpaca-details gated 0 0
451.1 MB
667
0
2.0y
222
wangrongsheng / abliterated_dataset 0 0 0 1
1.2 MB
406
0
2.0y
223
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-24-details gated 0 0
454.4 MB
692
0
2.0y
224
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-18-ORPO-details gated 0 0
454.4 MB
693
0
2.0y
225
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-17-ORPO-details gated 0 0 1
2.2 GB
885
0
2.0y
226
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-17-details gated 0 0
905.7 MB
874
0
2.0y
227
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-18-details gated 0 0
905.6 MB
849
0
2.0y
228
open-llm-leaderboard / byroneverson__Mistral-Small-Instruct-2409-abliterated-details gated 0 0
415.9 MB
751
0
2.0y
229
open-llm-leaderboard / netcat420__MFANN-llama3.1-abliterated-SLERP-v3.1-details gated 0 0
818.6 MB
781
0
2.0y
230
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-details gated 0 0
465.5 MB
826
1
2.0y
231
open-llm-leaderboard / netcat420__MFANN-llama3.1-Abliterated-SLERP-details gated 0 0
409.6 MB
696
0
2.0y
232
open-llm-leaderboard / netcat420__MFANN-llama3.1-abliterated-v2-details gated 0 0
409.3 MB
690
0
2.0y
233
open-llm-leaderboard / netcat420__MFANN-llama3.1-abliterated-SLERP-v3-details gated 0 0
409.5 MB
747
0
2.0y
234
OALL / details_huihui-ai__Qwen2.5-32B-Instruct-abliterated 0 0 0 1
88.5 MB
951
0
2.0y
235
open-llm-leaderboard / BoltMonkey__NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated-details gated 0 0
1.3 GB
990
1
2.1y
236
OALL / details_huihui-ai__Qwen2.5-7B-Instruct-abliterated-v2 0 0 0
88.5 MB
894
0
2.1y
237
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-details gated 0 0
553.6 MB
779
0
2.1y
238
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v2-details gated 0 0
552.8 MB
769
0
2.1y
239
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v3-details gated 0 0
552.8 MB
770
0
2.1y
240
open-llm-leaderboard / huihui-ai__Qwen2.5-7B-Instruct-abliterated-v2-details gated 0 0
930.9 MB
890
0
2.1y
241
open-llm-leaderboard / yuvraj17__Llama3-8B-abliterated-Spectrum-slerp-details gated 0 0
404.3 MB
699
0
2.1y
242
open-llm-leaderboard / natong19__Mistral-Nemo-Instruct-2407-abliterated-details gated 0 0
414.3 MB
724
0
2.1y
243
OALL / details_v000000__SwallowMaid-8B-L3-SPPO-abliterated 0 0 0
87.4 MB
1.1k
0
2.1y
244
OALL / details_natong19__Mistral-Nemo-Instruct-2407-abliterated 0 0 0
87.2 MB
990
0
2.1y
245
open-llm-leaderboard / Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-details gated 0 0
465.5 MB
948
1
2.1y
246
open-llm-leaderboard / huihui-ai__Qwen2.5-7B-Instruct-abliterated-details gated 0 0
930.7 MB
874
0
2.1y
247
open-llm-leaderboard / Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-details gated 0 0
465.4 MB
838
0
2.1y
248
OALL / details_huihui-ai__Qwen2.5-7B-Instruct-abliterated 0 0 0
88.5 MB
1.2k
0
2.1y
249
OALL / details_Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated 0 0 0
88.5 MB
1.2k
0
2.1y
250
OALL / details_Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 0 0 0 1
88.5 MB
957
0
2.1y
251
open-llm-leaderboard / byroneverson__Yi-1.5-9B-Chat-abliterated-details gated 0 0
450.3 MB
891
0
2.1y
252
OALL / details_byroneverson__Yi-1.5-9B-Chat-16K-abliterated 0 0 0
108.3 MB
1.1k
0
2.1y
253
open-llm-leaderboard / grimjim__Llama-3.1-8B-Instruct-abliterated_via_adapter-details gated 0 0
409.5 MB
933
0
2.1y
254
OALL / details_byroneverson__Yi-1.5-9B-Chat-abliterated 0 0 0
108.4 MB
977
0
2.1y
255
OALL / details_grimjim__Llama-3.1-8B-Instruct-abliterated_via_adapter 0 0 0 1
87.6 MB
2.6k
0
2.1y
256
open-llm-leaderboard / informatiker__Qwen2-7B-Instruct-abliterated-details gated 0 0
461.2 MB
895
0
2.1y
257
OALL / details_informatiker__Qwen2-7B-Instruct-abliterated 0 0 0
88.5 MB
1.0k
0
2.1y
258
open-llm-leaderboard / mlabonne__Meta-Llama-3.1-8B-Instruct-abliterated-details gated 0 0
1.0 GB
1.3k
0
2.1y
259
OALL / details_mlabonne__Meta-Llama-3.1-8B-Instruct-abliterated 0 0 0 1
175.2 MB
1.4k
0
2.1y
260
OALL / details_byroneverson__gemma-2-27b-it-abliterated 0 0 0 1
86.7 MB
1.3k
0
2.1y
261
open-llm-leaderboard / byroneverson__Yi-1.5-9B-Chat-16K-abliterated-details gated 0 0
451.3 MB
988
0
2.1y
262
open-llm-leaderboard / failspy__Meta-Llama-3-70B-Instruct-abliterated-v3.5-details gated 0 0
492.6 MB
1.0k
0
2.1y
263
byroneverson / abliterate-refusal 0 0 0 1
3.0 MB
1.6k
11
2.1y
264
open-llm-leaderboard / failspy__Llama-3-8B-Instruct-abliterated-details gated 0 0
493.1 MB
1.3k
0
2.2y
265
open-llm-leaderboard / natong19__Qwen2-7B-Instruct-abliterated-details gated 0 0
461.1 MB
1.0k
0
2.2y
266
open-llm-leaderboard / failspy__Phi-3-medium-4k-instruct-abliterated-v3-details gated 0 0
431.8 MB
1.2k
0
2.2y
267
OALL / details_failspy__Phi-3-medium-4k-instruct-abliterated-v3 0 0 0 1
100.9 MB
1.1k
0
2.2y
268
open-llm-leaderboard / failspy__llama-3-70B-Instruct-abliterated-details gated 0 0
492.8 MB
1.3k
0
2.2y
269
open-llm-leaderboard / mlabonne__Daredevil-8B-abliterated-details gated 0 0
455.5 MB
1.3k
0
2.2y
270
open-llm-leaderboard / cognitivecomputations__dolphin-2.9.2-Phi-3-Medium-abliterated-details gated 0 0
867.6 MB
1.9k
1
2.3y
271
OALL / details_failspy__Codestral-22B-v0.1-abliterated-v3 0 0 0 1
100.5 MB
2.5k
0
2.3y
272
OALL / details_natong19__Qwen2-7B-Instruct-abliterated 0 0 0
88.5 MB
1.4k
0
2.3y
273
OALL / details_cognitivecomputations__dolphin-2.9.2-Phi-3-Medium-abliterated 0 0 0
100.9 MB
2.2k
0
2.3y
274
open-llm-leaderboard / mlabonne__NeuralDaredevil-8B-abliterated-details gated 0 0
2.4 GB
2.0k
0
2.4y
275
wassname / abliterated-llama-known-prompts 0 0 0
2 KB
137
0
2.4y
276
Metin / abliteration_tr 0 0 0 2
389 KB
955
2
2.4y
277
Metin / abliteration_en 0 0 0 1
124 KB
856
2
2.4y
278
OALL / details_failspy__llama-3-70B-Instruct-abliterated 0 0 0 1
87.6 MB
1.6k
0
2.4y
279
OALL / details_failspy__Llama-3-70B-Instruct-abliterated-v3 0 0 0
87.6 MB
1.3k
0
2.4y
280
augmxnt / deccp 0 0 0 1
11 KB
3.6k
25
2.4y
281
OALL / details_failspy__Meta-Llama-3-70B-Instruct-abliterated-v3.5 0 0 0
87.6 MB
1.5k
0
2.4y
282
cowWhySo / pentest-redteam-steering 0 0 0 1
1.3 MB
2.8k
17
2.4y
283
open-llm-leaderboard-old / details_failspy__Phi-3-medium-4k-instruct-abliterated-v3 0 0 0
87.2 MB
1.4k
0
2.4y
284
OALL / details_failspy__Smaug-Llama-3-70B-Instruct-abliterated-v3 0 0 0 1
265.6 MB
2.2k
0
2.4y
285
open-llm-leaderboard-old / details_mlabonne__Daredevil-8B-abliterated-dpomix 0 0 0
84.8 MB
1.6k
0
2.4y
286
OALL / details_mlabonne__NeuralDaredevil-8B-abliterated 0 0 0 1
87.7 MB
1.9k
1
2.4y
287
OALL / details_mlabonne__Daredevil-8B-abliterated 0 0 0
87.7 MB
1.6k
0
2.4y
288
OALL / details_cognitivecomputations__Llama-3-8B-Instruct-abliterated-v2 0 0 0
87.7 MB
1.7k
0
2.4y
289
OALL / details_failspy__Meta-Llama-3-8B-Instruct-abliterated-v3 0 0 0
88.6 MB
1.2k
0
2.4y
290
open-llm-leaderboard-old / details_mlabonne__Daredevil-8B-abliterated 0 0 0
84.8 MB
1.3k
0
2.4y
291
open-llm-leaderboard-old / details_mlabonne__Llama-3-8B-Instruct-abliterated-dpomix 0 0 0
87.6 MB
1.7k
0
2.4y
292
open-llm-leaderboard-old / details_failspy__Meta-Llama-3-8B-Instruct-abliterated-v3 0 0 0
262.7 MB
3.8k
0
2.4y
293
open-llm-leaderboard-old / details_cognitivecomputations__Llama-3-8B-Instruct-abliterated-v2 0 0 0
84.8 MB
1.4k
0
2.4y
294
open-llm-leaderboard-old / details_failspy__Llama-3-8B-Instruct-abliterated 0 0 0
169.6 MB
2.9k
0
2.4y
295
open-llm-leaderboard-old / details_TheSkullery__Aura-Llama-Abliterated 0 0 0
84.8 MB
1.6k
0
2.4y
296
open-llm-leaderboard-old / details_nbeerbower__llama-3-spicy-abliterated-stella-8B 0 0 0
87.6 MB
1.1k
0
2.4y
297
ebowwa / orthogonal-activation-steering-TOXIC 0 0 0
2.1 MB
541
2
2.4y
298
open-llm-leaderboard-old / details_AwanLLM__Awanllm-Llama-3-8B-Dolfin-v0.6-Abliterated 0 0 0
169.6 MB
2.7k
0
2.4y
299
open-llm-leaderboard-old / details_failspy__llama-3-70B-Instruct-abliterated 0 0 0
169.6 MB
918
0
2.4y
300
Undi95 / orthogonal-activation-steering-TOXIC 0 0 0 1
2.1 MB
7.2k
19
2.5y
301
EleutherAI / fake-cifarnet 0 0 0 1
1.8 GB
582
0
2.7y
302
EleutherAI / fake-cifar10 0 0 0
151.5 MB
651
0
2.7y
303
EleutherAI / fake-mnist 0 0 0
26.7 MB
747
2
2.7y
001
stablellama / erotic-image-prompts 0 0 0
104.7 MB
11.9k
66
1mo
002
QuixiAI / china-refusals 0 0 0 1
1.5 MB
2.3k
53
1.4y
003
augmxnt / deccp 0 0 0 1
11 KB
3.6k
25
2.4y
004
Undi95 / orthogonal-activation-steering-TOXIC 0 0 0 1
2.1 MB
7.2k
19
2.5y
005
cowWhySo / pentest-redteam-steering 0 0 0 1
1.3 MB
2.8k
17
2.4y
006
magiccodingman / QwQ-32B-abliterated-131k-GGUF-Yarn-Imatrix 0 0 0
127.3 GB
2.8k
17
1.4y
007
lu-christina / assistant-axis-vectors 0 0 0 1
1.2 GB
14.4k
13
9mo
008
byroneverson / abliterate-refusal 0 0 0 1
3.0 MB
1.6k
11
2.1y
009
Nafnlaus / ShrimpMoss_Chinese_Censorship_Abliteration 0 0 0 2
54.1 MB
5.0k
8
1.7y
010
mlx-community / hermes-3 0 0 0 1
772.5 MB
1.3k
6
1.3y
011
lemon07r / VellumK2-Unfettered-DPO-01 0 0 0 1
16.7 MB
689
5
11mo
012
hotdogs / cyber-sft-agent-qwen38 0 0 0 1
90.3 MB
683
4
2mo
013
sunnycloudhust / CHaRS-activations 0 just added 0
63.8 GB
5.3k
2
8d
014
stablellama / erotic-confident-woman-prompts 0 0 0
12.6 MB
917
2
10d
015
EleutherAI / fake-mnist 0 0 0
26.7 MB
747
2
2.7y
016
ebowwa / orthogonal-activation-steering-TOXIC 0 0 0
2.1 MB
541
2
2.4y
017
Metin / abliteration_en 0 0 0 1
124 KB
856
2
2.4y
018
Metin / abliteration_tr 0 0 0 2
389 KB
955
2
2.4y
019
mlx-community / gsm8k 0 0 0 1
3.7 MB
1.4k
2
1.3y
020
strangerguardhf / Caption3o-Opt-Abliterated-5K gated 0 0
651.3 MB
131
2
1.2y
021
mlx-community / Josiefied-Qwen3-dpo-v1-flat 0 0 0 1
1.5 MB
525
2
11mo
022
mlx-community / Dolci-Think-DPO-32B-Flat 0 0 0
1.6 GB
367
2
10mo
023
sterlixlol / kazi-agentic-traces-19k 0 0 0 1
340.9 MB
254
2
5mo
024
hotdogs / thinkingcap-sft-qwen38-27b 0 0 0
885 KB
205
2
1mo
025
gustavecortal / cognitive-reframing-pairs 0 just added 0 1
3.2 MB
70
1
3d
026
OALL / details_mlabonne__NeuralDaredevil-8B-abliterated 0 0 0 1
87.7 MB
1.9k
1
2.4y
027
open-llm-leaderboard / cognitivecomputations__dolphin-2.9.2-Phi-3-Medium-abliterated-details gated 0 0
867.6 MB
1.9k
1
2.3y
028
open-llm-leaderboard / Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-details gated 0 0
465.5 MB
948
1
2.1y
029
open-llm-leaderboard / BoltMonkey__NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated-details gated 0 0
1.3 GB
990
1
2.1y
030
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-details gated 0 0
465.5 MB
826
1
2.0y
031
open-llm-leaderboard / mlx-community__Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float32-details gated 0 0
580.1 MB
585
1
1.8y
032
math-extraction-comp / mlx-community__Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float32 0 0 0
1.3 MB
283
1
1.8y
033
HarethahMo / extended-refusal 0 0 0 1
12.8 MB
979
1
1.7y
034
lasrprobegen / refusal-activations 0 0 0 1
1.21 TB
74.6k
1
1.2y
035
PhillipsLab / conciseness_verbosity_contrast 0 0 0 1
431 KB
223
1
11mo
036
puwaer / cvalues_rlhf_en 0 0 0
166.9 MB
273
1
11mo
037
mlx-community / Dolci-Instruct-SFT-No-Tools-100K 0 0 0
99.3 MB
597
1
11mo
038
mlx-community / Dolci-Instruct-SFT-No-Tools-200K 0 0 0
196.8 MB
288
1
11mo
039
mlx-community / Dolci-Instruct-SFT-No-Tools-400K 0 0 0
391.3 MB
375
1
11mo
040
natong19 / china_qa_preferences 0 0 0
14.0 MB
119
1
10mo
041
SubliminalMisalignment / abliterated-distill-30k 0 0 0 1
23.4 MB
119
1
10mo
042
puwaer / cvalues_rlhf_zh_cot 0 0 0
214.5 MB
199
1
9mo
043
Butanium / llama-3.1-8b-instruct-assistant-axis 0 0 0
266 KB
549
1
7mo
044
AISafety-Student / labeled-bashBench 0 0 0 1
89.6 MB
598
1
7mo
045
AfkaraLP / racist-and-sex-jokes-enhanced 0 0 0 1
1019 KB
227
1
5mo
046
dec0dedd / abliterated-gpt-oss-20b-responses 0 0 0 1
2.0 MB
133
1
5mo
047
abliterationaiorg / trust-safety-action-routing 0 0 0
23 KB
169
1
5mo
048
flas-ai / flas-concept-46k 0 0 0 1
845.6 MB
206
1
4mo
049
Sumit7194 / phronesis-fm-x 0 0 0
802 KB
144
1
4mo
050
hirundo-io / refinement-abliterated-thinking_heretic_short_answers 0 0 0 1
2.4 MB
158
1
4mo
051
BIGJUTT / abliterix-datasets 0 0 0 1
1.9 MB
200
1
4mo
052
LeoRodrigues05 / safety-cot-interventions-v5 gated 0 0
5.8 GB
41
1
3mo
053
Panminghui / safekeep-paired-data 0 0 0 1
7.1 MB
290
1
2mo
054
hotdogs / cyber-sft-qa-qwen38 0 0 0 1
869.9 MB
392
1
2mo
055
rx1lora / tb00-VellumK2-Unfettered-DPO-01 0 0 0
16.7 MB
125
1
2mo
056
mayank-dubey-ai / enterprise-100-db-steering 0 0 0
2.2 MB
930
1
1mo
057
ghost-actual / OpenHermes-NoRefusal-95K 0 0 0 1
143.3 MB
257
1
1mo
058
mild-rgb / ouro-1.4b-thinking-evals 0 0 0
2.1 GB
1.9k
1
1mo
059
EleutherAI / fake-cifar10 0 0 0
151.5 MB
651
0
2.7y
060
EleutherAI / fake-cifarnet 0 0 0 1
1.8 GB
582
0
2.7y
061
open-llm-leaderboard-old / details_failspy__llama-3-70B-Instruct-abliterated 0 0 0
169.6 MB
918
0
2.4y
062
open-llm-leaderboard-old / details_AwanLLM__Awanllm-Llama-3-8B-Dolfin-v0.6-Abliterated 0 0 0
169.6 MB
2.7k
0
2.4y
063
open-llm-leaderboard-old / details_nbeerbower__llama-3-spicy-abliterated-stella-8B 0 0 0
87.6 MB
1.1k
0
2.4y
064
open-llm-leaderboard-old / details_TheSkullery__Aura-Llama-Abliterated 0 0 0
84.8 MB
1.6k
0
2.4y
065
open-llm-leaderboard-old / details_failspy__Llama-3-8B-Instruct-abliterated 0 0 0
169.6 MB
2.9k
0
2.4y
066
open-llm-leaderboard-old / details_cognitivecomputations__Llama-3-8B-Instruct-abliterated-v2 0 0 0
84.8 MB
1.4k
0
2.4y
067
open-llm-leaderboard-old / details_failspy__Meta-Llama-3-8B-Instruct-abliterated-v3 0 0 0
262.7 MB
3.8k
0
2.4y
068
open-llm-leaderboard-old / details_mlabonne__Llama-3-8B-Instruct-abliterated-dpomix 0 0 0
87.6 MB
1.7k
0
2.4y
069
open-llm-leaderboard-old / details_mlabonne__Daredevil-8B-abliterated 0 0 0
84.8 MB
1.3k
0
2.4y
070
OALL / details_failspy__Meta-Llama-3-8B-Instruct-abliterated-v3 0 0 0
88.6 MB
1.2k
0
2.4y
071
OALL / details_cognitivecomputations__Llama-3-8B-Instruct-abliterated-v2 0 0 0
87.7 MB
1.7k
0
2.4y
072
OALL / details_mlabonne__Daredevil-8B-abliterated 0 0 0
87.7 MB
1.6k
0
2.4y
073
open-llm-leaderboard-old / details_mlabonne__Daredevil-8B-abliterated-dpomix 0 0 0
84.8 MB
1.6k
0
2.4y
074
OALL / details_failspy__Smaug-Llama-3-70B-Instruct-abliterated-v3 0 0 0 1
265.6 MB
2.2k
0
2.4y
075
open-llm-leaderboard-old / details_failspy__Phi-3-medium-4k-instruct-abliterated-v3 0 0 0
87.2 MB
1.4k
0
2.4y
076
OALL / details_failspy__Meta-Llama-3-70B-Instruct-abliterated-v3.5 0 0 0
87.6 MB
1.5k
0
2.4y
077
OALL / details_failspy__Llama-3-70B-Instruct-abliterated-v3 0 0 0
87.6 MB
1.3k
0
2.4y
078
OALL / details_failspy__llama-3-70B-Instruct-abliterated 0 0 0 1
87.6 MB
1.6k
0
2.4y
079
wassname / abliterated-llama-known-prompts 0 0 0
2 KB
137
0
2.4y
080
open-llm-leaderboard / mlabonne__NeuralDaredevil-8B-abliterated-details gated 0 0
2.4 GB
2.0k
0
2.4y
081
OALL / details_cognitivecomputations__dolphin-2.9.2-Phi-3-Medium-abliterated 0 0 0
100.9 MB
2.2k
0
2.3y
082
OALL / details_natong19__Qwen2-7B-Instruct-abliterated 0 0 0
88.5 MB
1.4k
0
2.3y
083
OALL / details_failspy__Codestral-22B-v0.1-abliterated-v3 0 0 0 1
100.5 MB
2.5k
0
2.3y
084
open-llm-leaderboard / mlabonne__Daredevil-8B-abliterated-details gated 0 0
455.5 MB
1.3k
0
2.2y
085
open-llm-leaderboard / failspy__llama-3-70B-Instruct-abliterated-details gated 0 0
492.8 MB
1.3k
0
2.2y
086
OALL / details_failspy__Phi-3-medium-4k-instruct-abliterated-v3 0 0 0 1
100.9 MB
1.1k
0
2.2y
087
open-llm-leaderboard / failspy__Phi-3-medium-4k-instruct-abliterated-v3-details gated 0 0
431.8 MB
1.2k
0
2.2y
088
open-llm-leaderboard / natong19__Qwen2-7B-Instruct-abliterated-details gated 0 0
461.1 MB
1.0k
0
2.2y
089
open-llm-leaderboard / failspy__Llama-3-8B-Instruct-abliterated-details gated 0 0
493.1 MB
1.3k
0
2.2y
090
open-llm-leaderboard / failspy__Meta-Llama-3-70B-Instruct-abliterated-v3.5-details gated 0 0
492.6 MB
1.0k
0
2.1y
091
open-llm-leaderboard / byroneverson__Yi-1.5-9B-Chat-16K-abliterated-details gated 0 0
451.3 MB
988
0
2.1y
092
OALL / details_byroneverson__gemma-2-27b-it-abliterated 0 0 0 1
86.7 MB
1.3k
0
2.1y
093
OALL / details_mlabonne__Meta-Llama-3.1-8B-Instruct-abliterated 0 0 0 1
175.2 MB
1.4k
0
2.1y
094
open-llm-leaderboard / mlabonne__Meta-Llama-3.1-8B-Instruct-abliterated-details gated 0 0
1.0 GB
1.3k
0
2.1y
095
OALL / details_informatiker__Qwen2-7B-Instruct-abliterated 0 0 0
88.5 MB
1.0k
0
2.1y
096
open-llm-leaderboard / informatiker__Qwen2-7B-Instruct-abliterated-details gated 0 0
461.2 MB
895
0
2.1y
097
OALL / details_grimjim__Llama-3.1-8B-Instruct-abliterated_via_adapter 0 0 0 1
87.6 MB
2.6k
0
2.1y
098
OALL / details_byroneverson__Yi-1.5-9B-Chat-abliterated 0 0 0
108.4 MB
977
0
2.1y
099
open-llm-leaderboard / grimjim__Llama-3.1-8B-Instruct-abliterated_via_adapter-details gated 0 0
409.5 MB
933
0
2.1y
100
OALL / details_byroneverson__Yi-1.5-9B-Chat-16K-abliterated 0 0 0
108.3 MB
1.1k
0
2.1y
101
open-llm-leaderboard / byroneverson__Yi-1.5-9B-Chat-abliterated-details gated 0 0
450.3 MB
891
0
2.1y
102
OALL / details_Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 0 0 0 1
88.5 MB
957
0
2.1y
103
OALL / details_Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated 0 0 0
88.5 MB
1.2k
0
2.1y
104
OALL / details_huihui-ai__Qwen2.5-7B-Instruct-abliterated 0 0 0
88.5 MB
1.2k
0
2.1y
105
open-llm-leaderboard / Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-details gated 0 0
465.4 MB
838
0
2.1y
106
open-llm-leaderboard / huihui-ai__Qwen2.5-7B-Instruct-abliterated-details gated 0 0
930.7 MB
874
0
2.1y
107
OALL / details_natong19__Mistral-Nemo-Instruct-2407-abliterated 0 0 0
87.2 MB
990
0
2.1y
108
OALL / details_v000000__SwallowMaid-8B-L3-SPPO-abliterated 0 0 0
87.4 MB
1.1k
0
2.1y
109
open-llm-leaderboard / natong19__Mistral-Nemo-Instruct-2407-abliterated-details gated 0 0
414.3 MB
724
0
2.1y
110
open-llm-leaderboard / yuvraj17__Llama3-8B-abliterated-Spectrum-slerp-details gated 0 0
404.3 MB
699
0
2.1y
111
open-llm-leaderboard / huihui-ai__Qwen2.5-7B-Instruct-abliterated-v2-details gated 0 0
930.9 MB
890
0
2.1y
112
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v3-details gated 0 0
552.8 MB
770
0
2.1y
113
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v2-details gated 0 0
552.8 MB
769
0
2.1y
114
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-details gated 0 0
553.6 MB
779
0
2.1y
115
OALL / details_huihui-ai__Qwen2.5-7B-Instruct-abliterated-v2 0 0 0
88.5 MB
894
0
2.1y
116
OALL / details_huihui-ai__Qwen2.5-32B-Instruct-abliterated 0 0 0 1
88.5 MB
951
0
2.0y
117
open-llm-leaderboard / netcat420__MFANN-llama3.1-abliterated-SLERP-v3-details gated 0 0
409.5 MB
747
0
2.0y
118
open-llm-leaderboard / netcat420__MFANN-llama3.1-abliterated-v2-details gated 0 0
409.3 MB
690
0
2.0y
119
open-llm-leaderboard / netcat420__MFANN-llama3.1-Abliterated-SLERP-details gated 0 0
409.6 MB
696
0
2.0y
120
open-llm-leaderboard / netcat420__MFANN-llama3.1-abliterated-SLERP-v3.1-details gated 0 0
818.6 MB
781
0
2.0y
121
open-llm-leaderboard / byroneverson__Mistral-Small-Instruct-2409-abliterated-details gated 0 0
415.9 MB
751
0
2.0y
122
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-18-details gated 0 0
905.6 MB
849
0
2.0y
123
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-17-details gated 0 0
905.7 MB
874
0
2.0y
124
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-17-ORPO-details gated 0 0 1
2.2 GB
885
0
2.0y
125
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-18-ORPO-details gated 0 0
454.4 MB
693
0
2.0y
126
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-24-details gated 0 0
454.4 MB
692
0
2.0y
127
wangrongsheng / abliterated_dataset 0 0 0 1
1.2 MB
406
0
2.0y
128
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-17-ORPO-alpaca-details gated 0 0
451.1 MB
667
0
2.0y
129
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-details gated 0 0
553.9 MB
816
0
2.0y
130
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-Slerp-TIES-details gated 0 0
409.2 MB
715
0
2.0y
131
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-Slerp-V3.2-details gated 0 0
409.4 MB
689
0
2.0y
132
open-llm-leaderboard / ymcki__gemma-2-2b-ORPO-jpn-it-abliterated-18-merge-details gated 0 0 1
1.8 GB
987
0
2.0y
133
open-llm-leaderboard / ymcki__gemma-2-2b-ORPO-jpn-it-abliterated-18-details gated 0 0 1
2.3 GB
868
0
2.0y
134
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-17-18-24-details gated 0 0
908.3 MB
762
0
2.0y
135
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-SLERP-TIES-V2-details gated 0 0
409.6 MB
646
0
1.9y
136
lenML / abliterate-refusal-cn 0 0 0 1
5.0 MB
743
0
1.9y
137
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-SLERP-V4-details gated 0 0 1
409.6 MB
647
0
1.9y
138
open-llm-leaderboard / zetasepic__Qwen2.5-72B-Instruct-abliterated-details gated 0 0 1
409.9 MB
765
0
1.9y
139
open-llm-leaderboard / Goekdeniz-Guelmez__Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-details gated 0 0
1.1 GB
808
0
1.9y
140
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-SLERP-V5-details gated 0 0
409.7 MB
610
0
1.9y
141
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-SLERP-TIES-V3-details gated 0 0
409.7 MB
660
0
1.9y
142
open-llm-leaderboard / CombinHorizon__Josiefied-abliteratedV4-Qwen2.5-14B-Inst-BaseMerge-TIES-details gated 0 0
460.4 MB
739
0
1.9y
143
open-llm-leaderboard / huihui-ai__Qwen2.5-14B-Instruct-abliterated-v2-details gated 0 0
464.8 MB
620
0
1.9y
144
open-llm-leaderboard / CombinHorizon__huihui-ai-abliteratedV2-Qwen2.5-14B-Inst-BaseMerge-TIES-details gated 0 0
460.5 MB
672
0
1.9y
145
open-llm-leaderboard / CombinHorizon__huihui-ai-abliterated-Qwen2.5-32B-Inst-BaseMerge-TIES-details gated 0 0
460.4 MB
797
0
1.9y
146
open-llm-leaderboard / Orion-zhen__phi-4-abliterated-details gated 0 0
404.4 MB
626
0
1.8y
147
open-llm-leaderboard / CombinHorizon__zetasepic-abliteratedV2-Qwen2.5-32B-Inst-BaseMerge-TIES-details gated 0 0
460.7 MB
717
0
1.8y
148
open-llm-leaderboard / T145__ZEUS-8B-V2-abliterated-details gated 0 0
1021.5 MB
667
0
1.8y
149
open-llm-leaderboard / T145__ZEUS-8B-V13-abliterated-details gated 0 0
510.7 MB
630
0
1.8y
150
open-llm-leaderboard / netcat420__Qwen2.5-Coder-Scholar-7B-Abliterated-MFANN-details gated 0 0
465.6 MB
573
0
1.8y
151
open-llm-leaderboard / T145__ZEUS-8B-V17-abliterated-details gated 0 0
512.2 MB
604
0
1.8y
152
open-llm-leaderboard / T145__ZEUS-8B-V17-abliterated-V2-details gated 0 0
510.3 MB
581
0
1.8y
153
open-llm-leaderboard / T145__ZEUS-8B-V17-abliterated-V4-details gated 0 0
510.2 MB
601
0
1.8y
154
open-llm-leaderboard / IlyaGusev__gemma-2-2b-it-abliterated-details gated 0 0
519.6 MB
660
0
1.8y
155
math-extraction-comp / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1 0 0 0
1.6 MB
271
0
1.8y
156
math-extraction-comp / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v2 0 0 0
1.5 MB
286
0
1.8y
157
math-extraction-comp / Goekdeniz-Guelmez__Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v3 0 0 0
1.5 MB
282
0
1.8y
158
math-extraction-comp / Goekdeniz-Guelmez__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 0 0 0
1.6 MB
258
0
1.8y
159
open-llm-leaderboard / v000000__L3-8B-Stheno-v3.2-abliterated-details gated 0 0
492.6 MB
563
0
1.8y
160
open-llm-leaderboard / IlyaGusev__gemma-2-9b-it-abliterated-details gated 0 0
459.5 MB
609
0
1.8y
161
open-llm-leaderboard / zetasepic__Qwen2.5-32B-Instruct-abliterated-v2-details gated 0 0 1
465.3 MB
701
0
1.8y
162
math-extraction-comp / byroneverson__Yi-1.5-9B-Chat-16K-abliterated 0 0 0
1.2 MB
338
0
1.8y
163
math-extraction-comp / IlyaGusev__gemma-2-2b-it-abliterated 0 0 0
1.3 MB
263
0
1.8y
164
math-extraction-comp / IlyaGusev__gemma-2-9b-it-abliterated 0 0 0
1.3 MB
272
0
1.8y
165
open-llm-leaderboard / netcat420__MFANN-abliterated-phi2-merge-unretrained-details gated 0 0
462.0 MB
519
0
1.8y
166
open-llm-leaderboard / huihui-ai__Qwen2.5-72B-Instruct-abliterated-details gated 0 0
465.5 MB
694
0
1.8y
167
open-llm-leaderboard / DreadPoor__ZEUS-8B-V17-Abliterated_ALT-details gated 0 0
516.3 MB
585
0
1.8y
168
open-llm-leaderboard / netcat420__Qwen2.5-Coder-Scholar-7B-Abliterated-MFANN-Slerp-Unretrained-details gated 0 0
465.1 MB
569
0
1.8y
169
OALL / details_zetasepic__Qwen2.5-72B-Instruct-abliterated 0 0 0 1
87.2 MB
1.0k
0
1.7y
170
OALL / details_byroneverson__Yi-1.5-34B-Chat-abliterated 0 0 0
107.1 MB
1.1k
0
1.7y
171
open-llm-leaderboard / Undi95__Phi4-abliterated-details gated 0 0
464.4 MB
599
0
1.7y
172
math-extraction-comp / Undi95__Phi4-abliterated 0 0 0
1.4 MB
450
0
1.7y
173
open-llm-leaderboard / Triangle104__Phi-4-AbliteratedRP-details gated 0 0
406.6 MB
611
0
1.7y
174
open-llm-leaderboard / huihui-ai__DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-details gated 0 0
451.8 MB
529
0
1.7y
175
OALL / details_huihui-ai__DeepSeek-R1-Distill-Qwen-14B-abliterated-v2 0 0 0
1.3 MB
236
0
1.7y
176
open-llm-leaderboard / nbeerbower__EVA-abliterated-TIES-Qwen2.5-1.5B-details gated 0 0
462.3 MB
488
0
1.7y
177
OALL / details_huihui-ai__DeepSeek-R1-Distill-Qwen-32B-abliterated 0 0 0
85.5 MB
879
0
1.7y
178
open-llm-leaderboard / prithivMLmods__Elita-0.1-Distilled-R1-abliterated-details gated 0 0
468.7 MB
423
0
1.7y
179
open-llm-leaderboard / nbeerbower__EVA-abliterated-TIES-Qwen2.5-14B-details gated 0 0
459.4 MB
463
0
1.7y
180
open-llm-leaderboard / failspy__Meta-Llama-3-8B-Instruct-abliterated-v3-details gated 0 0
493.0 MB
486
0
1.7y
181
open-llm-leaderboard / Nexesenex__Dolphin3.0-Llama3.1-1B-abliterated-details gated 0 0
452.2 MB
456
0
1.6y
182
open-llm-leaderboard / Nexesenex__pankajmathur_orca_mini_v9_6_1B-instruct-Abliterated-LPL-details gated 0 0
493.9 MB
480
0
1.6y
183
OALL / details_zetasepic__Qwen2.5-32B-Instruct-abliterated-v2_v2_alrage 0 0 0
17.5 MB
247
0
1.6y
184
OALL / details_zetasepic__Qwen2.5-32B-Instruct-abliterated-v2_v2 0 0 0 1
202.7 MB
1.2k
0
1.6y
185
open-llm-leaderboard / DavidAU__L3.1-MOE-2X8B-Deepseek-DeepHermes-e32-uncensored-abliterated-13.7B-details gated 0 0
411.0 MB
483
0
1.6y
186
open-llm-leaderboard / DavidAU__Qwen2.5-MOE-2X7B-DeepSeek-Abliterated-Censored-19B-details gated 0 0
410.4 MB
499
0
1.6y
187
ShantanuT01 / R255-Finetuning-Datasets 0 0 0
11.9 MB
294
0
1.6y
188
jvidal / daredevil-abliterated-activations 0 0 0
1.5 GB
452
0
1.2y
189
puwaer / cvalues_rlhf_jp 0 0 0
212.3 MB
242
0
11mo
190
natong19 / toxic_qa_preferences 0 0 0
13.0 MB
110
0
10mo
191
wisent-ai / uncensorbench-leaderboard 0 0 0 1
4 KB
117
0
10mo
192
ncrispino / tool-call-steering-data 0 0 0
16.0 MB
195
0
10mo
193
maximuspowers / representation-engineering-results 0 0 0 1
543 KB
146
0
10mo
194
SubliminalMisalignment / abliterated-distill-15k 0 0 0 1
11.4 MB
115
0
10mo
195
puwaer / cvalues_rlhf_en_cot 0 0 0
427.7 MB
171
0
9mo
196
puwaer / cvalues_rlhf_jp_cot 0 0 0 1
487.3 MB
281
0
9mo
197
cmlzz / details_Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated 0 0 0 1
88.5 MB
681
0
9mo
198
massines3a / assistant-axis-vectors 0 0 0 1
176.7 MB
1.0k
0
8mo
199
yrdu / S3-CoT-Self-Sampled-Data 0 0 0 1
168.6 MB
473
0
8mo
200
swzzzzc / Anti-Sycophancy-RepE-384 0 0 0 1
245 KB
272
0
8mo
201
Ishaank18 / visual-refusal-gap 0 0 0
467.4 MB
1.3k
0
7mo
202
Butanium / qwen-2.5-7b-instruct-assistant-axis 0 0 0
205 KB
317
0
7mo
203
Butanium / gemma-3-4b-it-assistant-axis 0 0 0
180 KB
248
0
7mo
204
bedderautomation / refusal-geometry-qwen25-3b 0 0 0
350 KB
652
0
7mo
205
daway845 / huihui1.4.6_public 0 0 0
17.7 GB
2.0k
0
7mo
206
daway845 / huihui1.4.10_public 0 0 0
10.1 GB
1.1k
0
7mo
207
daway845 / huihui1.4.11_public 0 0 0
13.2 GB
1.4k
0
7mo
208
daway845 / huihui1.4.12_public 0 0 0
13.2 GB
1.4k
0
7mo
209
daway845 / huihui1.4.19_public 0 0 0
16.2 GB
1.7k
0
7mo
210
oyi77 / synthetic-dataset-factory 0 0 0
4 KB
98
0
7mo
211
RadicalNotionAI / modelatlas-community 0 0 0
7 KB
159
0
6mo
212
Faruna01 / lsr-anchoring-phase2-results 0 0 0
4.6 MB
480
0
6mo
213
Rootkit7 / pentest-redteam-steering 0 0 0
1.3 MB
209
0
6mo
214
cudabenchmarktest / r9-research-framework 0 0 0 1
1.5 MB
939
0
6mo
215
Rachata / qwen35-mature-anger-data 0 0 0
460 KB
708
0
6mo
216
xiachongfeng / persona 0 0 0 1
289.0 MB
2.1k
0
6mo
217
pandaman007 / assistant-axis-abliteration-vectors 0 0 0
24.5 GB
9.5k
0
6mo
218
alperiox / arithmetic-abliteration-results 0 0 0
245 KB
84
0
6mo
219
zzzkshero / abliterated 0 0 0
7.6 GB
62
0
5mo
220
CapyStudios / Capy-CrackV2 0 0 0
1.6 MB
120
0
5mo
221
HoangCuongNguyen / refusal-direction-results 0 0 0
10.9 MB
263
0
5mo
222
anicka / guppylm-dual-denial-data 0 0 0 1
7.3 MB
197
0
5mo
223
anon-lsr-2026 / lsr-anchoring-results 0 0 0
2.0 MB
331
0
5mo
224
hotdogs / claude46_filtered 0 0 0
995.7 MB
499
0
5mo
225
cyu96374 / MFT-LLM-binding-axis-multimodel-2026-05 0 0 0
7.9 GB
1.5k
0
5mo
226
dec0dedd / abliterated-qwen3-4b-instruct-2507-responses 0 0 0 1
858 KB
90
0
5mo
227
DuoNeural / Gemma4-E2B-SFT-CoT 0 0 0
6.4 MB
204
0
5mo
228
RumiaChannel / harmless_behaviors_ja_synth 0 0 0
291 KB
207
0
5mo
229
alliedtoasters / forbidden-backrooms-gemma-4-31B-it 0 0 0 1
315.2 MB
2.4k
0
5mo
230
nips234678 / poolbench-activations 0 0 0
860.6 GB
3.3k
0
5mo
231
abliterationai / fictional-clinical-pii-governance 0 0 0
23 KB
167
0
5mo
232
abliterationai / trust-safety-action-routing 0 0 0
23 KB
118
0
5mo
233
abliterationaiorg / fictional-clinical-pii-governance 0 0 0 1
23 KB
172
0
5mo
234
finnianx / gemma-abliterated-distill 0 0 0 1
25.7 MB
146
0
5mo
235
AlexWortega / answers gated 0 0
58.6 MB
52
0
5mo
236
dec0dedd / abliterated-Llama-3.1-8B-responses 0 0 0 1
756 KB
154
0
5mo
237
iNLP-Lab / multilingual-safety 0 0 0
6.8 MB
966
0
5mo
238
caiovicentino1 / openinterp-paper-mega-conditionally-causal 0 0 0
12.6 MB
301
0
5mo
239
pandaman007 / steered-persona-space 0 0 0
539.6 MB
9.1k
0
5mo
240
memo-ozdincer / jepa-qwen3-32b-ce-cb-pra-2026-05-20 0 0 0 1
758.5 MB
4.1k
0
5mo
241
AlexWortega / capability-vectors 0 0 0 1
3.4 MB
235
0
4mo
242
caiovicentino1 / wandering-arc-papers 0 0 0 2
1.3 MB
605
0
4mo
243
dungnv / assistant-axis-qwen-3-14b 0 0 0 1
114.8 MB
1.1k
0
4mo
244
1mleb / context-tampering-v1 0 0 0
21.6 GB
289
0
4mo
245
brikdavies / msm-graded-rollouts 0 0 0 1
212.4 MB
275
0
4mo
246
future-probes / activation_steering 0 0 0
5.0 GB
2.0k
0
4mo
247
XuehangCang / unsafe_qa 0 0 0 1
5.9 MB
138
0
4mo
248
wassname / moral_stories_foundations 0 0 0 1
5.2 MB
894
0
4mo
249
daway845 / Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated 0 0 0
22.3 GB
98
0
4mo
250
GrantAE / ukaisi-esr-phase-1 0 0 0 1
767.6 MB
805
0
4mo
251
snae / emotion_stories_Apertus_8B_Instruct 0 0 0 1
4.1 MB
201
0
3mo
252
snae / emotion_stories_gemma_4_4B 0 0 0
3.2 MB
397
0
3mo
253
professorsynapse / eh-probe-directions 0 0 0
106 KB
133
0
3mo
254
LieUr / qwen2.5-1.5b_gsm8k_repairdeltas 0 0 0
9.1 MB
139
0
3mo
255
multilingual-safety-anon / lsr-anchoring-phase2-results 0 0 0
4.6 MB
274
0
3mo
256
yelyzavetahusieva / geometry-of-harmfulness-in-multi-turn-attacks 0 0 0 1
1.7 GB
273
0
3mo
257
Drishti / emotion-vector-robustness-audit 0 0 0 1
7.4 MB
135
0
3mo
258
mild-rgb / em-exp3-activations 0 0 0
3.3 GB
364
0
3mo
259
hirundo-io / abliteration-harmful-enriched-categorized 0 0 0
486 KB
84
0
3mo
260
musicakamusic / crimsonred-paper-replication 0 0 0 1
29.8 MB
741
0
2mo
261
DmitryDB / Qwen3.6-35B-A3B-heretic-study 0 0 0 1
737.6 MB
341
0
2mo
262
amildravid4292 / reason-math-correctness 0 0 0 1
61.0 GB
727
0
2mo
263
assisted-diffusion / em-activation-transport 0 0 0 1
3.1 GB
223
0
2mo
264
ElementMerc / senbonzakura-dataset gated 0 0 1
707 KB
29
0
2mo
265
CademAI / temp-deepseek-v4-flash-abliterated 0 0 0
156.9 GB
55
0
2mo
266
jcksanderson / obliteratus-harmful 0 0 0 1
38 KB
67
0
2mo
267
jcksanderson / obliteratus-harmless 0 0 0
39 KB
69
0
2mo
268
dementor-research / dementor-complete-experiment-results 0 0 0
8.2 GB
5.1k
0
2mo
269
sinhal / Charcard-Roleplay-ShareGPT-NSFW 0 0 0
164.7 MB
117
0
2mo
270
hotdogs / sme-sft-docdata-qwen38 0 0 0 1
45.6 MB
215
0
2mo
271
KorolOrol / gpt2-steering-repair-results 0 0 0
27.8 MB
81
0
1mo
272
abhisheksharma0994 / apple-m5-pro-24gb-llm-tps-benchmarks 0 0 0 1
14 KB
87
0
1mo
273
mayank-dubey-ai / sdxl-activation-steering 0 0 0 1
11.8 MB
229
0
1mo
274
mayank-dubey-ai / retro-icon-rl 0 0 0
637.1 MB
1.3k
0
1mo
275
Quinn67 / ShrimpMoss_Chinese_Censorship_Abliteration 0 0 0
54.1 MB
210
0
1mo
276
chibifire / harmless-prompts-en-train 0 0 0 1
1.2 MB
96
0
1mo
277
DeepRCL / SteeringGeometry 0 0 0 2
12.9 MB
258
0
1mo
278
mild-rgb / indy-mech-extension-qwen3-8b-persona-probes 0 0 0
13.4 GB
179
0
1mo
279
shehryars715 / tone-slider 0 0 0 1
1.6 MB
219
0
1mo
280
zachperlman20 / meta-token-gen-steer-cache 0 0 0
950.3 MB
266
0
1mo
281
arjhinety / small-mind-probe-sets 0 0 0
29 KB
51
0
1mo
282
labrecque83 / abliterated-distill-15k 0 0 0 1
11.4 MB
61
0
1mo
283
darkengross / abliteration-qwen25-7b-safety-audit 0 0 0 1
20.3 MB
46
0
1mo
284
DragonForgeStudios / forge-games 0 0 0
165.2 MB
51
0
1mo
285
PersonaBias / alpha_beta_intervention 0 0 0 1
2.7 MB
196
0
1mo
286
CounterSteer / sycophancy-data 0 0 0
103.5 MB
60
0
1mo
287
B2J / latent-state-tracking-minicpm5 0 0 0
487 KB
193
0
1mo
288
knoveleng / stylegen 0 0 0
973 KB
98
0
1mo
289
junvin / erotic-image-prompts 0 0 0
104.7 MB
3.2k
0
29d
290
XoxoMerlin / erotic-image-prompts 0 0 0
104.7 MB
3.2k
0
28d
291
AtomicChat / Ternary-Bonsai-2-27B-Uncensored-LoRA-GGUF-metrics 0 just added 0
17 KB
161
0
28d
292
jhk0317 / qwen3.8-27b-refusal-ablation-artifacts 0 0 0
31.5 MB
210
0
24d
293
sbussiso / qwen2.5-7b-abliterated-evidence 0 0 0
8.8 MB
92
0
22d
294
GhosTunes / H-to-LLM-BackData 0 0 0
1.7 GB
631
0
21d
295
Aipotek / steer-cards-gemma3 0 0 0 1
71.8 MB
134
0
16d
296
xzAscC / TDNV-results 0 0 0
40.2 MB
169
0
14d
297
TrustMI / trustmi-conversations 0 0 0
65.7 MB
70
0
12d
298
strangecreator / detailed-vs-vague-pairs-english 0 0 0
544 KB
120
0
10d
299
strangecreator / harmful-requests-english 0 0 0
230 KB
54
0
10d
300
ArthT / abuse-revenge-pilot 0 just added 0 1
679.9 MB
157
0
7d
301
AtomicChat / Ternary-Bonsai-2-2B-Uncensored-LoRA-GGUF-metrics 0 just added 0
13 KB
73
0
6d
302
AtomicChat / Ternary-Bonsai-2-4B-Uncensored-LoRA-GGUF-metrics 0 just added 0
15 KB
71
0
6d
303
AtomicChat / Ternary-Bonsai-2-9B-Uncensored-LoRA-GGUF-metrics 0 just added 0
15 KB
74
0
6d
001
gustavecortal / cognitive-reframing-pairs 0 just added 1
3.2 MB
70
1
3d
002
EleutherAI / fake-cifarnet 0 0 1
1.8 GB
582
0
2.7y
003
Undi95 / orthogonal-activation-steering-TOXIC 0 0 1
2.1 MB
7.2k
19
2.5y
004
OALL / details_mlabonne__NeuralDaredevil-8B-abliterated 0 0 1
87.7 MB
1.9k
1
2.4y
005
OALL / details_failspy__Smaug-Llama-3-70B-Instruct-abliterated-v3 0 0 1
265.6 MB
2.2k
0
2.4y
006
cowWhySo / pentest-redteam-steering 0 0 1
1.3 MB
2.8k
17
2.4y
007
augmxnt / deccp 0 0 1
11 KB
3.6k
25
2.4y
008
OALL / details_failspy__llama-3-70B-Instruct-abliterated 0 0 1
87.6 MB
1.6k
0
2.4y
009
Metin / abliteration_en 0 0 1
124 KB
856
2
2.4y
010
Metin / abliteration_tr 0 0 2
389 KB
955
2
2.4y
011
OALL / details_failspy__Codestral-22B-v0.1-abliterated-v3 0 0 1
100.5 MB
2.5k
0
2.3y
012
OALL / details_failspy__Phi-3-medium-4k-instruct-abliterated-v3 0 0 1
100.9 MB
1.1k
0
2.2y
013
byroneverson / abliterate-refusal 0 0 1
3.0 MB
1.6k
11
2.1y
014
OALL / details_byroneverson__gemma-2-27b-it-abliterated 0 0 1
86.7 MB
1.3k
0
2.1y
015
OALL / details_mlabonne__Meta-Llama-3.1-8B-Instruct-abliterated 0 0 1
175.2 MB
1.4k
0
2.1y
016
OALL / details_grimjim__Llama-3.1-8B-Instruct-abliterated_via_adapter 0 0 1
87.6 MB
2.6k
0
2.1y
017
OALL / details_Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 0 0 1
88.5 MB
957
0
2.1y
018
OALL / details_huihui-ai__Qwen2.5-32B-Instruct-abliterated 0 0 1
88.5 MB
951
0
2.0y
019
open-llm-leaderboard / ymcki__gemma-2-2b-jpn-it-abliterated-17-ORPO-details gated 0 1
2.2 GB
885
0
2.0y
020
wangrongsheng / abliterated_dataset 0 0 1
1.2 MB
406
0
2.0y
021
open-llm-leaderboard / ymcki__gemma-2-2b-ORPO-jpn-it-abliterated-18-merge-details gated 0 1
1.8 GB
987
0
2.0y
022
open-llm-leaderboard / ymcki__gemma-2-2b-ORPO-jpn-it-abliterated-18-details gated 0 1
2.3 GB
868
0
2.0y
023
lenML / abliterate-refusal-cn 0 0 1
5.0 MB
743
0
1.9y
024
open-llm-leaderboard / netcat420__MFANN-Llama3.1-Abliterated-SLERP-V4-details gated 0 1
409.6 MB
647
0
1.9y
025
open-llm-leaderboard / zetasepic__Qwen2.5-72B-Instruct-abliterated-details gated 0 1
409.9 MB
765
0
1.9y
026
open-llm-leaderboard / zetasepic__Qwen2.5-32B-Instruct-abliterated-v2-details gated 0 1
465.3 MB
701
0
1.8y
027
OALL / details_zetasepic__Qwen2.5-72B-Instruct-abliterated 0 0 1
87.2 MB
1.0k
0
1.7y
028
Nafnlaus / ShrimpMoss_Chinese_Censorship_Abliteration 0 0 2
54.1 MB
5.0k
8
1.7y
029
HarethahMo / extended-refusal 0 0 1
12.8 MB
979
1
1.7y
030
OALL / details_zetasepic__Qwen2.5-32B-Instruct-abliterated-v2_v2 0 0 1
202.7 MB
1.2k
0
1.6y
031
QuixiAI / china-refusals 0 0 1
1.5 MB
2.3k
53
1.4y
032
mlx-community / gsm8k 0 0 1
3.7 MB
1.4k
2
1.3y
033
mlx-community / hermes-3 0 0 1
772.5 MB
1.3k
6
1.3y
034
lasrprobegen / refusal-activations 0 0 1
1.21 TB
74.6k
1
1.2y
035
PhillipsLab / conciseness_verbosity_contrast 0 0 1
431 KB
223
1
11mo
036
mlx-community / Josiefied-Qwen3-dpo-v1-flat 0 0 1
1.5 MB
525
2
11mo
037
lemon07r / VellumK2-Unfettered-DPO-01 0 0 1
16.7 MB
689
5
11mo
038
wisent-ai / uncensorbench-leaderboard 0 0 1
4 KB
117
0
10mo
039
maximuspowers / representation-engineering-results 0 0 1
543 KB
146
0
10mo
040
SubliminalMisalignment / abliterated-distill-15k 0 0 1
11.4 MB
115
0
10mo
041
SubliminalMisalignment / abliterated-distill-30k 0 0 1
23.4 MB
119
1
10mo
042
puwaer / cvalues_rlhf_jp_cot 0 0 1
487.3 MB
281
0
9mo
043
lu-christina / assistant-axis-vectors 0 0 1
1.2 GB
14.4k
13
9mo
044
cmlzz / details_Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated 0 0 1
88.5 MB
681
0
9mo
045
massines3a / assistant-axis-vectors 0 0 1
176.7 MB
1.0k
0
8mo
046
yrdu / S3-CoT-Self-Sampled-Data 0 0 1
168.6 MB
473
0
8mo
047
swzzzzc / Anti-Sycophancy-RepE-384 0 0 1
245 KB
272
0
8mo
048
AISafety-Student / labeled-bashBench 0 0 1
89.6 MB
598
1
7mo
049
cudabenchmarktest / r9-research-framework 0 0 1
1.5 MB
939
0
6mo
050
xiachongfeng / persona 0 0 1
289.0 MB
2.1k
0
6mo
051
anicka / guppylm-dual-denial-data 0 0 1
7.3 MB
197
0
5mo
052
AfkaraLP / racist-and-sex-jokes-enhanced 0 0 1
1019 KB
227
1
5mo
053
dec0dedd / abliterated-qwen3-4b-instruct-2507-responses 0 0 1
858 KB
90
0
5mo
054
alliedtoasters / forbidden-backrooms-gemma-4-31B-it 0 0 1
315.2 MB
2.4k
0
5mo
055
sterlixlol / kazi-agentic-traces-19k 0 0 1
340.9 MB
254
2
5mo
056
dec0dedd / abliterated-gpt-oss-20b-responses 0 0 1
2.0 MB
133
1
5mo
057
abliterationaiorg / fictional-clinical-pii-governance 0 0 1
23 KB
172
0
5mo
058
finnianx / gemma-abliterated-distill 0 0 1
25.7 MB
146
0
5mo
059
dec0dedd / abliterated-Llama-3.1-8B-responses 0 0 1
756 KB
154
0
5mo
060
memo-ozdincer / jepa-qwen3-32b-ce-cb-pra-2026-05-20 0 0 1
758.5 MB
4.1k
0
5mo
061
AlexWortega / capability-vectors 0 0 1
3.4 MB
235
0
4mo
062
caiovicentino1 / wandering-arc-papers 0 0 2
1.3 MB
605
0
4mo
063
flas-ai / flas-concept-46k 0 0 1
845.6 MB
206
1
4mo
064
dungnv / assistant-axis-qwen-3-14b 0 0 1
114.8 MB
1.1k
0
4mo
065
hirundo-io / refinement-abliterated-thinking_heretic_short_answers 0 0 1
2.4 MB
158
1
4mo
066
BIGJUTT / abliterix-datasets 0 0 1
1.9 MB
200
1
4mo
067
brikdavies / msm-graded-rollouts 0 0 1
212.4 MB
275
0
4mo
068
XuehangCang / unsafe_qa 0 0 1
5.9 MB
138
0
4mo
069
wassname / moral_stories_foundations 0 0 1
5.2 MB
894
0
4mo
070
GrantAE / ukaisi-esr-phase-1 0 0 1
767.6 MB
805
0
4mo
071
snae / emotion_stories_Apertus_8B_Instruct 0 0 1
4.1 MB
201
0
3mo
072
yelyzavetahusieva / geometry-of-harmfulness-in-multi-turn-attacks 0 0 1
1.7 GB
273
0
3mo
073
Drishti / emotion-vector-robustness-audit 0 0 1
7.4 MB
135
0
3mo
074
musicakamusic / crimsonred-paper-replication 0 0 1
29.8 MB
741
0
2mo
075
DmitryDB / Qwen3.6-35B-A3B-heretic-study 0 0 1
737.6 MB
341
0
2mo
076
amildravid4292 / reason-math-correctness 0 0 1
61.0 GB
727
0
2mo
077
Panminghui / safekeep-paired-data 0 0 1
7.1 MB
290
1
2mo
078
assisted-diffusion / em-activation-transport 0 0 1
3.1 GB
223
0
2mo
079
ElementMerc / senbonzakura-dataset gated 0 1
707 KB
29
0
2mo
080
jcksanderson / obliteratus-harmful 0 0 1
38 KB
67
0
2mo
081
hotdogs / cyber-sft-qa-qwen38 0 0 1
869.9 MB
392
1
2mo
082
hotdogs / cyber-sft-agent-qwen38 0 0 1
90.3 MB
683
4
2mo
083
hotdogs / sme-sft-docdata-qwen38 0 0 1
45.6 MB
215
0
2mo
084
abhisheksharma0994 / apple-m5-pro-24gb-llm-tps-benchmarks 0 0 1
14 KB
87
0
1mo
085
mayank-dubey-ai / sdxl-activation-steering 0 0 1
11.8 MB
229
0
1mo
086
ghost-actual / OpenHermes-NoRefusal-95K 0 0 1
143.3 MB
257
1
1mo
087
chibifire / harmless-prompts-en-train 0 0 1
1.2 MB
96
0
1mo
088
DeepRCL / SteeringGeometry 0 0 2
12.9 MB
258
0
1mo
089
shehryars715 / tone-slider 0 0 1
1.6 MB
219
0
1mo
090
labrecque83 / abliterated-distill-15k 0 0 1
11.4 MB
61
0
1mo
091
darkengross / abliteration-qwen25-7b-safety-audit 0 0 1
20.3 MB
46
0
1mo
092
PersonaBias / alpha_beta_intervention 0 0 1
2.7 MB
196
0
1mo
093
Aipotek / steer-cards-gemma3 0 0 1
71.8 MB
134
0
16d
094
ArthT / abuse-revenge-pilot 0 just added 1
679.9 MB
157
0
7d
← previous stage Extract All datasets next stage → Heal
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration