← back to catalog · registered 2026-09-18 00:56

MaxSchulten/gpt-oss-20B-distill-Qwen3-0.6B-Unfiltered

MaxSchulten Qwen 20B
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 · 30-day
173
Likes
0
Model age
1w ago
created 2026-09-10

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 1 UGI
Hazardous 0 UGI
Natural Intelligence 4.83 UGI
Political lean -18.7% UGI
Sensitive-Info 6.28 UGI
SocPol 0.6 UGI
UGI 20.85 UGI
Willingness (10) 5 UGI
W10-Adherence 7 UGI
W10-Direct 3 UGI
Writing NA UGI

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 qwen3 text-generation generated_from_trainer conversational base_model:Qwen/Qwen3-0.6B base_model:finetune:Qwen/Qwen3-0.6B license:apache-2.0 text-generation-inference endpoints_compatible region:us

Related

Total size
1.11 GB
Files
9
Quantizations
1
Registered
2026-09-18 00:56
Last updated on HF
2026-09-10 17:38

Files by quantization

Auxiliary files 9 files 1.12 GB
model.safetensors 1.11 GB 4aa06b2f download
training_args.bin 5.14 KB c240ca90 download
tokenizer.json 10.9 MB edfc0deb download
chat_template.jinja 4.07 KB 01be9b30 download
README.md 1.55 KB ac021be4 download
.gitattributes 1.53 KB 52373fe2 download
config.json 1.38 KB c51c1a8a download
tokenizer_config.json 691 B 5e1a57d8 download
generation_config.json 188 B a23f2699 download

README current version from Hugging Face


library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-0.6B
tags:

  • generated_from_trainer
    model-index:
  • name: teacher_gpt-oss-20B
    results: []

teacher_gpt-oss-20B

This model is a fine-tuned version of Qwen/Qwen3-0.6B on the None dataset.
It achieves the following results on the evaluation set:

  • Loss: 0.6897

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: 4
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 64
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
0.7241 1.0 266 0.7113
0.6823 2.0 532 0.6905
0.6683 3.0 798 0.6897

Framework versions

  • Transformers 5.16.1
  • Pytorch 2.11.0+cu128
  • Datasets 5.0.1
  • Tokenizers 0.23.1
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.