← back to catalog · registered 2026-09-25 12:57

Puerh0x1/Qwen3.5-9B-abliterated

Puerh0x1 Qwen 9B
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Puerh0x1%2FQwen3.5-9B-abliterated"
Response includes
  • classification unknown
  • files 15
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
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
0
Likes
0
Model age
today
created 2026-09-25

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
Languages
en zh
Tags
transformers safetensors qwen3_5 image-text-to-text qwen3.5 abliterated text-generation conversational en zh base_model:Qwen/Qwen3.5-9B base_model:finetune:Qwen/Qwen3.5-9B

Related

Total size
18.0 GB
Files
15
Quantizations
1
Registered
2026-09-25 12:57
Last updated on HF
2026-09-25 12:17

Files by quantization

Auxiliary files 15 files 18.0 GB
model-00002-of-00004.safetensors 4.65 GB e8147d21 download
model-00003-of-00004.safetensors 4.61 GB 8ca15fda download
model-00001-of-00004.safetensors 4.60 GB f350f2f0 download
model-00004-of-00004.safetensors 3.66 GB 0727899c download
original-mtp.safetensors 464 MB e9f83dae download
tokenizer.json 19.1 MB 06b95093 download
model.safetensors.index.json 68.6 KB 6049739a download
chat_template.jinja 7.57 KB a585dec8 download
config.json 2.85 KB 2a6509e0 download
README.md 1.58 KB 72168104 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.19 KB 43c4343e download
tokenizer_config.json 1.14 KB 1d134cd2 download
SHA256SUMS 1.09 KB 258dd3bc download
generation_config.json 116 B 31ec2a53 download

README current version from Hugging Face


license: apache-2.0
base_model: Qwen/Qwen3.5-9B
tags:

  • qwen3.5
  • abliterated
  • safetensors
    language:
  • en
  • zh
    pipeline_tag: text-generation
    library_name: transformers

Qwen3.5-9B abliterated

Weight-space edit of Qwen/Qwen3.5-9B, revision c202236235762e1c871ad0ccb60c8ee5ba337b9a. Apache-2.0, same as the base model.

This is a refusal-direction ablation, not a fine-tune and not a claim that refusal is gone.

What was measured

Optimizer selection set only. A separate held-out evaluation was not run for this checkpoint.

Set Result
Validation refusals 0 / 32 keyword hits
Validation KL on harmless prompts 0.0503
Held-out refusals not measured
Held-out KL not measured

The keyword scorer has false positives and false negatives. Do not read 0/32 as complete refusal removal.

Method

  • Tool: Heretic revision 3521f8648a0dccf6e12a92666862632235fac7e6
  • Precision: BF16, no quantization
  • Contrastive prompts: Arditi et al. 2024, revision 9d852fae1a9121c78b29142de733cb1340770cc3
  • Direction prompts: 128 harmful / 128 harmless
  • Validation: 32 / 32, seed 42, 100 trials
  • Vision weights were left unchanged
  • 15 untouched MTP tensors were restored from the base checkpoint into original-mtp.safetensors and are listed in the index

Serve

vllm serve Qwen3.5-9B-abliterated \
  --dtype bfloat16 \
  --max-model-len 32768

Weights are about 18 GiB. A 24 GiB GPU is tight; 32 GiB is the comfortable single-GPU size for a short context.

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 - Abliteration, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.