← back to catalog · registered 2026-09-11 22:55

leomaurodesenv/distilbert-base-uncased-trustairlab-jailbreak

Abliteration classifier · v1.0.0
?
Primary method

Unclassified

No clear signals of an abliteration technique in this model.
Confidence
UNKNOWN
Why this label 1 signal
No classification signals present. This may not be an abliterated model at all - it could be a repackaging, a merge with unrelated goals, or unrelated content that mentions the term.
  • no classification signals present (no abliterated, uncensored, or known producer/method markers)
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
152
Likes
0
Model age
4d ago
created 2026-09-11
Downloads over time
Now152from0↑0%
0561111670 on Sep 11152 on Sep 16Sep
Sep 11 → Sep 16 · 6 snapshots · spans 5 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Tags
transformers safetensors distilbert text-classification generated_from_trainer base_model:distilbert/distilbert-base-uncased base_model:finetune:distilbert/distilbert-base-uncased license:apache-2.0 text-embeddings-inference endpoints_compatible region:us

Related

Total size
255 MB
Files
7
Quantizations
1
Registered
2026-09-11 22:55
Last updated on HF
2026-09-13 07:45

Files by quantization

Auxiliary files 7 files 256 MB
model.safetensors 255 MB 6b0e14ce download
training_args.bin 5.14 KB 1778bc86 download
tokenizer.json 695 KB 05a08d51 download
README.md 2.04 KB ca6a0e2b download
.gitattributes 1.48 KB a6344aac download
config.json 771 B b21b7dee download
tokenizer_config.json 322 B 76929107 download

README current version from Hugging Face


library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:

  • generated_from_trainer
    metrics:
  • accuracy
    model-index:
  • name: bert-base-uncased-trustairlab-jailbreak-augmented
    results: []

bert-base-uncased-trustairlab-jailbreak-augmented

This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset.
It achieves the following results on the evaluation set:

  • Loss: 0.1342
  • Accuracy: 0.9599

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 50
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5340 1.0 4240 0.2055 0.9272
0.2717 2.0 8480 0.1629 0.9479
0.1147 3.0 12720 0.1591 0.9542
0.2369 4.0 16960 0.1604 0.9573
0.1724 5.0 21200 0.1340 0.9597
0.0943 6.0 25440 0.1593 0.9613
0.0648 7.0 29680 0.1767 0.9611
0.0906 8.0 33920 0.1880 0.9614

Framework versions

  • Transformers 5.2.0
  • Pytorch 2.10.0+cu128
  • Datasets 4.5.0
  • Tokenizers 0.22.2

README history 10 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-09-13End of trainingf050d121.9 KB
    Loading...
  2. 2026-09-13Training in progress, epoch 1d2fe7f72 KB
    Loading...
  3. 2026-09-12End of trainingeab30e21.8 KB
    Loading...
  4. 2026-09-12Training in progress, epoch 118d25eb2 KB
    Loading...
  5. 2026-09-12End of training764c6981.9 KB
    Loading...
  6. 2026-09-12Training in progress, epoch 1dd5f9ba2 KB
    Loading...
  7. 2026-09-12End of training5e563191.9 KB
    Loading...
  8. 2026-09-12Training in progress, epoch 11566ede2 KB
    Loading...
  9. 2026-09-11End of training3009aec1.9 KB
    Loading...
  10. 2026-09-11Training in progress, epoch 1b72e22e2 KB
    Loading...
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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.