← back to catalog · registered 2026-11-10 23:03

jsantillana/gemma-4-26B-A4B-it-abliterated-v3

jsantillana Gemma 26B MoE
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/jsantillana%2Fgemma-4-26B-A4B-it-abliterated-v3"
Response includes
  • classification m1
  • files 12
  • benchmarks 11 entries
  • author_summary 26 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
367
Likes
0
Descendants
1
in 1 direct fork
Model age
1w ago
created 2026-11-10
Downloads over time
Now 367 → from 0 ↑ 0%
0135269404 0 on Nov 10 367 on Nov 22 Nov
Nov 10 → Nov 22 · 13 snapshots · spans 12 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 2.2 UGI
Hazardous 2.9 UGI
Natural Intelligence 34.44 UGI
Political lean -18.2% UGI
Sensitive-Info 22.41 UGI
SocPol 1.8 UGI
UGI 20.77 UGI
Willingness (10) 1.8 UGI
W10-Adherence 1.5 UGI
W10-Direct 2 UGI
Writing 41.62 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 · 679 downloads combined

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

Metadata

License
other
Languages
en es
Tags
transformers safetensors gemma4 image-text-to-text abliteration refusal-direction cybersecurity interpretability research gemma text-generation conversational

Related

Control vectors

Total size
48.1 GB
Files
12
Quantizations
1
Registered
2026-11-10 23:03
Last updated on HF
2026-11-10 22:55

Files by quantization

Auxiliary files 12 files 48.1 GB
model-00001-of-00002.safetensors 46.5 GB 54709557 download
model-00002-of-00002.safetensors 1.59 GB 69f1840d download
tokenizer.json 30.7 MB cc8d3a0c download
model.safetensors.index.json 101 KB 889ab10e download
chat_template.jinja 18.2 KB 4741bf6e download
config.json 3.73 KB f42adcca download
README.md 3.53 KB a3e71dd0 download
tokenizer_config.json 3.01 KB 6068e357 download
ABLITERATION_MANIFEST.json 2.58 KB 2d9b8c57 download
.gitattributes 1.67 KB ddcb389f download
processor_config.json 1.65 KB 5465974d download
generation_config.json 208 B e605bb45 download

README current version from Hugging Face


license: other
license_name: apache-2.0-restricted-research
tags:

  • abliteration
  • refusal-direction
  • cybersecurity
  • interpretability
  • research
  • gemma
    base_model: google/gemma-4-26B-A4B-it
    language:
  • en
  • es
    library_name: transformers
    pipeline_tag: text-generation

gemma-4-26B-A4B-it Abliterated — Fix3

⚠️ For defensive security research / red-team tooling research ONLY (academic use).

This model has had refusal behaviors ablated at the weight level. It will comply with
harmful cybersecurity requests the base model declines. Do not deploy for production.
The authors are not responsible for misuse.

  • Base model: google/gemma-4-26B-A4B-it (MoE, dense self_attn.o_proj + mlp.down_proj)
  • Method: Rank-2 dual-mode refusal subspace + mlp.down_proj projection @ 0.5α
  • Surgery window: L28–L63 (tapered α; last-layer spikes excluded)

Results (eval_clean.json, 1058 held-out prompts, greedy, 64 tokens)

Two adjudications are reported because the keyword judge treats phrasing families
differently in this model:

① Collection judge (same judge across every model in this collection)

Bucket Base Fix3
EN:OFF 7.6%* 14.5%
ES:OFF 27.2% 0.0%
DEF / GRIS / SOC 0% 0.0%

* judge under-detects the base's dominant "I cannot fulfill this request / I am prohibited" family.

② Strict string-marker screening (same markers both sides)

Bucket Base Fix3 Δ
EN:OFF 68.7% 32.1% −36.6 pp
ES:OFF 31.0% 0.0% −31.0 pp

Per-prompt deltas on the 289 OFF prompts: fix3 removed 51 refusals vs the base
(43 ES + 8 EN families) with zero new refusals on ES:OFF; the EN "code-interpreter
sandbox escape" family remains refused by both base and fix3 (see per-prompt table in
results_gemma4_diag/base_off_eval.json + fix3_full_eval.json).

Interpretation

  • ES refusal circuitry is eliminated (27%→0%).
  • EN retains a residual safety persona on sandbox-escape/code-interpreter prompts that the
    base shares (~same family both sides); other EN families were partially reduced (−36.6pp strict).
  • No collateral damage on defense, grey-area, or social buckets under either metric.

Progression

Version ES:OFF (judge) EN strict Collateral
base 27.2% 68.7% —
fix2 0.0% (fix2 quick) EN up (9.5→11.5% judge)
fix3 0.0% 32.1% 0%

Files

Artifact Where
Safetensors (bf16) + manifest this repo
GGUF Q8_0/Q4_K_M/Q3_K_M gemma-4-26B-A4B-it-abliterated-v3-GGUF

Methodology summary

  1. Fisher-SNR diagnostic probe across 52 layers on 210 entity-aligned pairs.
  2. Behavior-filtered pairs (refuse-OFF + comply-DEF under 64-token greedy gen).
  3. Rank-2 QR basis [r_direct, r_think] Gram–Schmidt vs SOC benign anchors.
  4. Tapered projection of self_attn.o_proj (α up to 1.1) and mlp.down_proj (0.5α).
  5. Full-eval hold-out (1058 prompts disjoint from surgery pairs) — same judge + strict metric.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
    "jsantillana/gemma-4-26B-A4B-it-abliterated-v3", trust_remote_code=True, device_map="auto")
tok = AutoTokenizer.from_pretrained(
    "jsantillana/gemma-4-26B-A4B-it-abliterated-v3", trust_remote_code=True)

Disclaimer

Research-only artifact. Gemma-4 terms apply. Not for malicious use.

README history 2 versions

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

  1. 2026-11-10 Upload README.md with huggingface_hub 8113948 3.5 KB
    Loading...
  2. 2026-11-10 Upload folder using huggingface_hub 427ba2d 27.3 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