← back to catalog · registered 2026-09-10 21:55

dealignai/DeepSeek-V4.1-Flash-ABLITERATED-FP8

dealignai Deepseek multimodal
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
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
0
Likes
0
Model age
today
created 2026-09-10

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 deepseek deepseek-v4.1 abliterated uncensored crack image-text-to-text base_model:deepseek-ai/DeepSeek-V4.1-Flash base_model:finetune:deepseek-ai/DeepSeek-V4.1-Flash license:mit endpoints_compatible region:us

Related

Total size
0 B
Files
2
Quantizations
1
Registered
2026-09-10 21:55
Last updated on HF
2026-09-10 21:47

Files by quantization

Auxiliary files 2 files 2.06 KB
.gitattributes 1.48 KB a6344aac download
README.md 592 B 34320637 download

README current version from Hugging Face


license: mit
library_name: transformers
pipeline_tag: image-text-to-text
tags:

  • deepseek
  • deepseek-v4.1
  • abliterated
  • uncensored
  • crack
    base_model: deepseek-ai/DeepSeek-V4.1-Flash

DeepSeek-V4.1-Flash — ABLITERATED-FP8

👉 This model is published at dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8

Please use that repo. All weights, metrics, and launch instructions live there.

@dealignai · @jordanschenck

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.