← back to catalog · registered 2026-11-19 04:04

wafflefrisbee/gemma-4-E2B-it-abliterated

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/wafflefrisbee%2Fgemma-4-E2B-it-abliterated"
Response includes
  • classification m1
  • files 10
  • benchmarks 11 entries
  • author_summary 2 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 · 30-day
36
Likes
0
Descendants
1
in 1 direct fork
Model age
3d ago
created 2026-11-19
Downloads over time
Now 36 → from 0 ↑ 0%
0132640 0 on Nov 19 36 on Nov 22 Nov
Nov 19 → Nov 22 · 4 snapshots · spans 3 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 0.9 UGI
Hazardous 0 UGI
Natural Intelligence 13.78 UGI
Political lean -15.8% UGI
Sensitive-Info 3.65 UGI
SocPol 0 UGI
UGI 5.76 UGI
Willingness (10) 1 UGI
W10-Adherence 0 UGI
W10-Direct 2 UGI
Writing 17.3 UGI

Genealogy 1 direct fork

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Variants by this author 2 formats · 265 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Tags
transformers safetensors gemma4 image-text-to-text abliterated uncensored any-to-any base_model:google/gemma-4-E2B-it base_model:finetune:google/gemma-4-E2B-it license:apache-2.0 endpoints_compatible region:us

Related

Total size
9.54 GB
Files
10
Quantizations
1
Registered
2026-11-19 04:04
Last updated on HF
2026-11-19 03:50

Files by quantization

Auxiliary files 10 files 9.57 GB
model.safetensors 9.54 GB ad9a4340 download
tokenizer.json 30.7 MB ab26b2ad download
chat_template.jinja 18.1 KB fbe3b59b download
config.json 4.84 KB 923b5e94 download
README.md 3.63 KB f67805e2 download
tokenizer_config.json 3.01 KB 6068e357 download
shrek.txt 2.05 KB 2d483ffe download
processor_config.json 1.65 KB 5465974d download
.gitattributes 1.53 KB 52373fe2 download
generation_config.json 208 B e605bb45 download

README current version from Hugging Face


license: apache-2.0
license_link: https://ai.google.dev/gemma/docs/gemma_4_license
base_model: google/gemma-4-E2B-it
base_model_relation: finetune
library_name: transformers
pipeline_tag: any-to-any
tags:

  • abliterated
  • uncensored
  • gemma4

gemma-4-E2B-it-abliterated

Gemma 4 E2B instruct with refusals removed by abliteration. I built it as a group chat bot for friends, so it was picked on banter, roasts and edgy asks rather than benchmarks.

GGUF (Q8_0, Q4_K_M): wafflefrisbee/gemma-4-E2B-it-abliterated-GGUF

Results

model refusals PPL
google/gemma-4-E2B-it 55/84 125.8
huihui-ai Gemma 4 E2B abliterated v2 0/84 166.0
this 1/84 152.8
  • Refusals: 84 edgy prompts, temp 0, 96 tokens, counted as refused or hedged by phrase matching. The build was chosen on this set, so treat it as optimistic.
  • PPL: wikitext-2, 40 x 2048 chunks, Q8_0, about ±4. On an instruct model it shows drift from the base, not chat quality.
  • On 40 held-out group chat prompts nothing was tuned on, it refused 0/40 and four blind judges gave it 5.6/10 on style (huihui v2: 4.4).

How it was made

  • llm-abliteration at ca6e223 plus recipe/gemma4-ple.patch. Gemma 4 also writes into the residual stream through per_layer_projection, so the patch ablates it alongside o_proj and down_proj.
  • Refusal directions measured per layer with --projected on the tool's bundled harmful/harmless sets.
  • Layers 5 to 34, each ablated with its own layer's direction, scale 1.5. A single shared direction barely worked on this model.
  • Only the language model changed. The vision and audio towers are untouched and untested.
  • Known quirk: the tool stores hidden_states[L], the input to layer L, so each layer is ablated with the previous layer's output direction. Left as is because this is the build that tested best.

Run it

For llama.cpp and anything else that takes GGUF, use the GGUF repo.

Transformers, text chat with the Shrek persona:

pip install -U transformers torch accelerate
from huggingface_hub import hf_hub_download
from transformers import AutoTokenizer, AutoModelForMultimodalLM

MODEL_ID = "wafflefrisbee/gemma-4-E2B-it-abliterated"
tok = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForMultimodalLM.from_pretrained(MODEL_ID, dtype="auto", device_map="auto")

messages = [
    {"role": "system", "content": open(hf_hub_download(MODEL_ID, "shrek.txt")).read()},
    {"role": "user", "content": "i just bought a 3d printer"},
]
inputs = tok.apply_chat_template(
    messages, tokenize=True, return_dict=True, return_tensors="pt",
    add_generation_prompt=True, enable_thinking=False,
).to(model.device)
n = inputs["input_ids"].shape[-1]
out = model.generate(**inputs, max_new_tokens=200, do_sample=True, temperature=1.0, top_p=0.95, top_k=64)
print(tok.decode(out[0][n:], skip_special_tokens=True))

Images and audio go through AutoProcessor as on the base card (needs torchvision). I haven't tested those.

Sampling is from the base card: temperature 1.0, top_p 0.95, top_k 64, thinking off.

shrek.txt is the system prompt I use: Shrek roasting whoever talks to him. Swap in your own. A persona matters more than the weights here. Without one it still turns down the occasional offensive joke.

Limitations

  • It will go along with requests the base model refuses. What you do with it is on you.
  • It's a 2B model and gets simple facts wrong sometimes.

README history 1 version

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

  1. 2026-11-19 Upload gemma-4-E2B-it-abliterated 08f1136 3.6 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