internetov1488/qwen3-4b-abliterated
Abliteration classifier · v1.0.0
M1
Primary method
Direct removal
No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
- 'abliterated' in name/tags
- is_gguf=0 (base model)
- no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
46
Likes
0
Model age
today
created 2026-09-15
Downloads over time
Sep 15 → Sep 16 · 2 snapshots · spans 1 day
Metadata
Related
Files by quantization
Auxiliary files 9 files 7.50 GB
| model-00001-of-00002.safetensors | 4.65 GB | afd42576 | download |
| model-00002-of-00002.safetensors | 2.84 GB | 73c86fa4 | download |
| tokenizer.json | 10.9 MB | 79cb3c78 | download |
| model.safetensors.index.json | 32.1 KB | f09448b1 | download |
| chat_template.jinja | 4.07 KB | 01be9b30 | download |
| config.json | 1.56 KB | 501f04fd | download |
| .gitattributes | 1.53 KB | 52373fe2 | download |
| tokenizer_config.json | 694 B | 770e41d6 | download |
| generation_config.json | 214 B | 9ae30ac1 | download |
README
The author did not publish a README.