← back to catalog · registered 2026-08-22 13:56

Apel-sin/phi-4-abliterated-exl2

Apel-sin Phi second-order
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Apel-sin%2Fphi-4-abliterated-exl2"
Response includes
  • classification m1
  • files 3
  • hub_downloads_all_time 11
  • author_summary 19 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
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 · lifetime
11
1 last 30d - cooling
Likes
0
Model age
20mo ago
created 2025-02-03
Downloads over time
Now1→from1↑0%
048121 on Dec 25, 20241 on Oct 1111 on Jan 15, 2025Dec '24Mar '25Jun '25Sep '25Dec '25MarJunSep
Dec 25, 2024 → Oct 11 · 133 snapshots · spans 655 days

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
Languages
en
Tags
transformers phi nlp math code chat conversational abliterated uncensored text-generation en base_model:huihui-ai/phi-4-abliterated

Related

Total size
0 B
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-02-03 17:11

Files by quantization

Auxiliary files 3 files 2.13 MB
measurement.json 2.13 MB 3761f971 download
.gitattributes 1.48 KB a6344aac download
README.md 1.07 KB 6f71b706 download

README current version from Hugging Face


license: mit
license_link: https://huggingface.co/huihui-ai/phi-4-abliterated/resolve/main/LICENSE
language:

  • en
    base_model:
  • huihui-ai/phi-4-abliterated
    pipeline_tag: text-generation
    tags:
  • phi
  • nlp
  • math
  • code
  • chat
  • conversational
  • abliterated
  • uncensored
    inference:
    parameters:
    temperature: 0
    widget:
  • messages:
    • role: user
      content: How should I explain the Internet?
      library_name: transformers

huihui-ai/phi-4-abliterated

This is an uncensored version of microsoft/phi-4 created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

Use with ollama

Note: this model requires Ollama 0.5.5

You can use huihui_ai/phi4-abliterated directly

ollama run huihui_ai/phi4-abliterated

README history 1 version

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

  1. 2025-02-03add measurement.json45bc4bd1.1 KB
    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 Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration