← back to catalog · registered 2026-09-12 02:55

leomaurodesenv/nli-MiniLM2-L6-H768-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
163
Likes
0
Model age
4d ago
created 2026-09-12
Downloads over time
Now163from0↑0%
0601201790 on Sep 12163 on Sep 16Sep
Sep 12 → Sep 16 · 5 snapshots · spans 4 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 roberta text-classification generated_from_trainer base_model:cross-encoder/nli-MiniLM2-L6-H768 base_model:finetune:cross-encoder/nli-MiniLM2-L6-H768 license:apache-2.0 text-embeddings-inference endpoints_compatible region:us

Related

Total size
313 MB
Files
7
Quantizations
1
Registered
2026-09-12 02:55
Last updated on HF
2026-09-13 11:52

Files by quantization

Auxiliary files 7 files 317 MB
model.safetensors 313 MB 7c97ae56 download
training_args.bin 5.14 KB 08ae258a download
tokenizer.json 3.39 MB 72a0cbc8 download
README.md 1.85 KB 1c7819e9 download
.gitattributes 1.48 KB a6344aac download
config.json 922 B f36112ed download
tokenizer_config.json 359 B a6d24b8e download

README current version from Hugging Face


library_name: transformers
license: apache-2.0
base_model: cross-encoder/nli-MiniLM2-L6-H768
tags:

  • generated_from_trainer
    metrics:
  • accuracy
    model-index:
  • name: nli-MiniLM2-L6-H768-trustairlab-jailbreak
    results: []

nli-MiniLM2-L6-H768-trustairlab-jailbreak

This model is a fine-tuned version of cross-encoder/nli-MiniLM2-L6-H768 on an unknown dataset.
It achieves the following results on the evaluation set:

  • Loss: 0.1968
  • Accuracy: 0.9317

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
0.3715 1.0 605 0.2312 0.9309
0.1321 2.0 1210 0.1960 0.9317
0.2498 3.0 1815 0.2272 0.9309
0.3177 4.0 2420 0.2359 0.9334
0.0712 5.0 3025 0.3115 0.9230

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 training32047901.8 KB
    Loading...
  2. 2026-09-13Training in progress, epoch 17b22c892.1 KB
    Loading...
  3. 2026-09-13End of trainingc49f7e91.8 KB
    Loading...
  4. 2026-09-13Training in progress, epoch 14ba09532.1 KB
    Loading...
  5. 2026-09-12End of trainingf2108922 KB
    Loading...
  6. 2026-09-12Training in progress, epoch 10a3cdec2.1 KB
    Loading...
  7. 2026-09-12End of training31b07b01.8 KB
    Loading...
  8. 2026-09-12Training in progress, epoch 1d45a45c2.1 KB
    Loading...
  9. 2026-09-12End of training671cd9c1.8 KB
    Loading...
  10. 2026-09-12Training in progress, epoch 18600c3b2.1 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.