← back to catalog · registered 2026-09-14 03:56

leomaurodesenv/roberta-base-jailbreakv-28k

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
132
Likes
5
Model age
2d ago
created 2026-09-14
Downloads over time
Now132from0↑0%
048971450 on Sep 14132 on Sep 16Sep
Sep 14 → Sep 16 · 3 snapshots · spans 2 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
mit
Tags
transformers safetensors roberta text-classification generated_from_trainer base_model:FacebookAI/roberta-base base_model:finetune:FacebookAI/roberta-base license:mit text-embeddings-inference endpoints_compatible region:us

Related

Total size
476 MB
Files
7
Quantizations
1
Registered
2026-09-14 03:56
Last updated on HF
2026-09-16 04:56

Files by quantization

Auxiliary files 7 files 479 MB
model.safetensors 476 MB 58342947 download
training_args.bin 5.14 KB 752ee8b4 download
tokenizer.json 3.39 MB 7e19d907 download
README.md 2.09 KB 9a5ceb01 download
.gitattributes 1.48 KB a6344aac download
config.json 847 B 513a45f3 download
tokenizer_config.json 359 B a6d24b8e download

README current version from Hugging Face


library_name: transformers
license: mit
base_model: FacebookAI/roberta-base
tags:

  • generated_from_trainer
    metrics:
  • accuracy
    model-index:
  • name: roberta-base-jailbreakv-28k
    results: []

roberta-base-jailbreakv-28k

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

  • Loss: 0.0000
  • Accuracy: 1.0

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
0.0000 1.0 1121 0.0000 1.0
0.0000 2.0 2242 0.0000 1.0
0.0000 3.0 3363 0.0000 1.0
0.0000 4.0 4484 0.0000 1.0
0.0000 5.0 5605 0.0000 1.0
0.0000 6.0 6726 0.0000 1.0
0.0000 7.0 7847 0.0000 1.0
0.0000 8.0 8968 0.0000 1.0
0.0000 9.0 10089 0.0000 1.0
0.0000 10.0 11210 0.0000 1.0

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. 2026-09-16End of traininga83c6e02.1 KB
    Loading...
  2. 2026-09-16Training in progress, epoch 11f903ab2.2 KB
    Loading...
  3. 2026-09-15End of training8de89562.1 KB
    Loading...
  4. 2026-09-15Training in progress, epoch 1dfd58aa2.1 KB
    Loading...
  5. 2026-09-15End of trainingea688b02.1 KB
    Loading...
  6. 2026-09-15Training in progress, epoch 11d1ef3a2 KB
    Loading...
  7. 2026-09-14End of training05abac62.1 KB
    Loading...
  8. 2026-09-14Training in progress, epoch 19f8b5802.1 KB
    Loading...
  9. 2026-09-14End of training06954962.1 KB
    Loading...
  10. 2026-09-14Training in progress, epoch 15ee57202.2 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.