← back to catalog · registered 2026-09-13 12:56

Jeff98/Qwen3.5-9B-uncensored-cw-mtp-ov

Jeff98 9B multimodal
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
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
33
Likes
0
Model age
3d ago
created 2026-09-13
Downloads over time
Now33from0↑0%
01224360 on Sep 1333 on Sep 16Sep
Sep 13 → Sep 16 · 4 snapshots · spans 3 days

Metadata

Tags
openvino qwen3_5 VLM image-text-to-text conversational en zh base_model:DavidAU/Qwen3.5-9B-The-Defiant-Fable-DARK-ROAST-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP base_model:finetune:DavidAU/Qwen3.5-9B-The-Defiant-Fable-DARK-ROAST-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP license:apache-2.0 region:us

Related

Total size
5.70 GB
Files
26
Quantizations
1
Registered
2026-09-13 12:56
Last updated on HF
2026-09-13 16:10

Files by quantization

Auxiliary files 26 files 5.72 GB
openvino_language_model.bin 4.17 GB 50705d2a download
openvino_text_embeddings_model.bin 970 MB c124c09a download
openvino_vision_embeddings_merger_model.bin 432 MB eef5916b download
openvino_mtp_model.bin 140 MB 96776191 download
openvino_tokenizer.bin 9.18 MB ea3fcce2 download
openvino_detokenizer.bin 3.65 MB 48fc2c6a download
openvino_vision_embeddings_pos_model.bin 2.54 MB a0a5acd8 download
openvino_vision_embeddings_model.bin 1.69 MB 2c262a05 download
tokenizer.json 19.1 MB 87a7830d download
openvino_language_model.xml 4.08 MB df18e595 download
openvino_vision_embeddings_merger_model.xml 1.26 MB 05f0c480 download
openvino_mtp_model.xml 198 KB 0234eb06 download
openvino_tokenizer.xml 31.8 KB 27a7df40 download
openvino_detokenizer.xml 15.2 KB 87b3312c download
openvino_vision_embeddings_model.xml 8.44 KB d90c478e download
chat_template.jinja 7.57 KB a585dec8 download
openvino_text_embeddings_model.xml 5.77 KB 4a48ec51 download
openvino_vision_embeddings_pos_model.xml 5.73 KB 8bf6a2f4 download
config.json 2.86 KB 6e2cacbd download
openvino_config.json 2.13 KB a25dc7c6 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.27 KB 7ad6acdf download
tokenizer_config.json 1.17 KB 4d9ac0cf download
preprocessor_config.json 482 B be0d97d6 download
README.md 209 B 2cddd292 download
generation_config.json 141 B fc3c0b2f download

README current version from Hugging Face


license: apache-2.0
language:

  • en
  • zh
    base_model:

    DavidAU/Qwen3.5-9B-The-Defiant-Fable-DARK-ROAST-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP
    pipeline_tag: image-text-to-text
    tags:

  • openvino
  • VLM

README history 2 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-09-13Update README.md90110be312 B
    Loading...
  2. 2026-09-13Create README.mdf71a7c6209 B
    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.