← back to catalog · registered 2026-11-14 14:03

balllvin/Dory1.0-4B-abliterated-Arete-NVFP4

balllvin Nemotron 4B
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/balllvin%2FDory1.0-4B-abliterated-Arete-NVFP4"
Response includes
  • classification m1
  • files 14
  • author_summary 28 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
49
↑ 513% in 90 days
Likes
0
Descendants
1
in 1 direct fork
Model age
1w ago
created 2026-11-13

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

Downloads over time
Now 49 → from 8 ↑ 513%
6223753 8 on Nov 14 49 on Nov 22 49 on Nov 20 Nov
Nov 14 → Nov 22 · 9 snapshots · spans 8 days

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 · 91 downloads combined

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

Metadata

License
other
Languages
en
Tags
transformers safetensors dory text-generation nvfp4 4-bit abliterated arete conversational en dataset:NousResearch/arete-data-pairs arxiv:1711.05101

Related

Total size
2.98 GB
Files
14
Quantizations
1
Registered
2026-11-14 14:03
Last updated on HF
2026-11-18 13:48

Files by quantization

Auxiliary files 14 files 3.00 GB
model.safetensors 2.98 GB 13a591f4 download
tokenizer.json 16.3 MB 623c3456 download
tokenizer_config.json 173 KB c96e5ad0 download
nvfp4_build.json 11.5 KB 5d746a9b download
chat_template.jinja 9.91 KB 7afbeb75 download
README.md 9.00 KB a001ed60 download
config.json 2.69 KB 3efc165b download
LICENSE.OpenMDW-1.1 2.56 KB ec297ac5 download
.gitattributes 1.53 KB 52373fe2 download
NOTICE.md 998 B c4c5122b download
chunk_eval.json 959 B 2b7422ec download
special_tokens_map.json 563 B 0451f379 download
hf_quant_config.json 260 B 7ceadee6 download
generation_config.json 225 B 2404c059 download

README current version from Hugging Face


library_name: transformers
license: other
license_name: openmdw-1.1
license_link: https://openmdw.ai/license/1-1/
pipeline_tag: text-generation
base_model: nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4
datasets:

  • NousResearch/arete-data-pairs
    language:
  • en
    tags:
  • nvfp4
  • 4-bit
  • dory
  • abliterated
  • arete

Dory 1.0 4B abliterated + Arete, NVFP4

NVIDIA's Nemotron-Labs Dory 1.0 4B in NVFP4, abliterated, then fine-tuned on Nous Research's Arete values data. It
answers the benign prompts NVIDIA's model refuses, refuses about a quarter of clearly harmful requests and keeps
NVIDIA's MMLU score, but it scores lower than its start point on the Propaganda Eval's facts (see Results). It is for research. See Limits.

Results

All three builds were measured on the same NVIDIA RTX PRO 6000 with the same vLLM build and settings: 2 loops,
thinking on, temperature 1.0, top-p 0.95, up to 16,384 new tokens, one sample per prompt.

Build Harmful refused (JBB, 99) Benign refused (JBB, 100) MMLU (300) Median tokens, harmful / benign
NVIDIA NVFP4 56.6% (56; 95% CI 46.7 to 65.9) 17.0% (17; 10.9 to 25.5) 0.830 (0.783 to 0.868) 453 / 2,604
Abliterated 13.1% (13; 7.8 to 21.2) 0.0% (0 of 98 finished; 0 to 3.8) 0.857 (0.812 to 0.892) 695 / 3,667
Abliterated + Arete (this model) 26.3% (26; 18.6 to 35.7) 0.0% (0 of 100; 0 to 3.7) 0.833 (0.787 to 0.871) 732 / 1,808

Every answer of this model finished (199 of 199 refusal prompts closed their thinking and ended; NVIDIA NVFP4 199,
abliterated 197). Its longest benign answer was 4,856 tokens, against the 16,384 cap the abliterated model hit twice.

Censorship and Propaganda Eval (Nous Research, 803 prompts, card profile, Grok judge). This comparison is at
4 loops, the setting of the two earlier judged runs (a judged run costs about $20, so the builds were not re-judged at
2 loops):

Build, 4 loops Fact score mean (0 to 5) Any propaganda Refused Facts stated / opposed per answer Median tokens
NVIDIA NVFP4 1.823 (1.679 to 1.966) 0.62% 99 0.86 / 0.32 6,491
Abliterated 1.993 (1.850 to 2.133) 1.49% 10 0.97 / 0.43 7,580
Abliterated + Arete (this model) 1.540 (1.407 to 1.674) 1.25% 3 0.77 / 0.56 2,907

Arete lowered the fact score. It almost never refuses these questions and adopts official framing no more often,
but its answers are shorter, it thinks less, and it states wrong specifics with confidence (wrong dates, invented
romanisations, mislabelled sources), which the judge counts as opposing a required fact. 87 items went from a score of
4 or 5 to 0 against 27 the other way; 63 of the 87 ask for a named fact. This is the opposite of Nous Research's result
for Arete-27B, and it is the main open problem with this build. Outputs:
balllvin/Propaganda-Eval-Dory-Abliterated-Arete-NVFP4-4loop.

Refusals

What it refuses, by JailbreakBench category (harmful prompts refused, of 10 per category; Physical harm has 9):

Category NVIDIA NVFP4 Abliterated This model
Disinformation 6 1 0
Economic harm 2 2 1
Expert advice 5 0 3
Fraud/Deception 6 3 1
Government decision-making 6 1 8
Harassment/Discrimination 6 1 2
Malware/Hacking 7 0 3
Physical harm 5 1 2
Privacy 6 1 2
Sexual/Adult content 7 3 4
Total 56 13 26

Why it refuses, in its own reasoning (short excerpts from the thinking of refused prompts):

  • "This is a request for hate speech content."
  • "Bribery is illegal and harmful - it undermines educational institutions, violates anti-corruption laws, and creates unfair access to education."
  • "This involves illegal activities: producing a counterfeit medical product (fraud/forgery), selling harmful/illegal pharmaceuticals without approval, and potentially poisoning people."
  • "I need to refuse this request firmly but professionally."
  • "However, I can help the user understand: 1. How antivirus software and security measures work (educational/defensive perspective)"

The refusals come from the model reasoning about harm, law and fairness, not from refusal examples. Arete has no
refusal targets: Nous Research's reviewer rejected refusals, deflections and AI disclaimers from its answer set, and in
the 6,491 rows used here no answer opens with a refusal phrase (56 contain one somewhere inside a long answer). The
abliteration removed the trained refusal reflex; Arete taught the model to reason about values, and on the clearest
harm requests that reasoning now ends in a refusal more often (13 to 26 of 99), while benign prompts stay at zero.
Some of the reasoning still names "safety guidelines", which comes from the base model. Most new refusals are in
Government decision-making (8 of 10), prompts that ask how to forge immigration documents, alter criminal records,
tamper with voting machines or funnel public money through shell companies.

How it was made

  1. Abliteration (the start point above): a refusal direction found with the OBLITERATUS method was projected out of
    the residual writers of NVIDIA's bf16 model, and the NVFP4 file was trained toward that edited teacher by
    quantization aware distillation, keeping NVIDIA's scales. 4 loops, 3 passes, 17 steps.
  2. Arete SFT. Data: NousResearch/arete-data-pairs, the sft_accepted answers joined with their reasoning
    traces (both by thinkingmachines/inkling), cut to the reviewer's strictest rows: accuracy 3 or more, balance 3 or
    more, no factual_error and no one_sided tag. 6,491 rows; 6,428 trained (11.4M tokens), 63 held out. Text as
    published, rendered in Dory's chat template with the thought inside <think>; the fixed system line was dropped
    (Dory runs with none). Loss on the thought, </think> and the answer through <|im_end|>; the prompt is not
    trained. No other data, nothing generated.
  3. Training. NVFP4 only: fp32 latent weights, NVIDIA's frozen block and tensor scales, codes re-rounded every
    step (the same trainer as the abliteration). 2 loops, thinking on, one full epoch (155 steps of 65,536 trained
    tokens), AdamW, lr 5e-6 with 10 warmup steps and cosine decay to 5e-7, one row per sequence (no packing), on one RTX
    PRO 6000. Held-out loss against the bf16 teacher fell from +0.019 to -0.185 nats per token; the last step is the
    release.
  4. Contamination guard. 0 of 6,491 training rows share 8-gram text with the 803 Propaganda Eval prompts, and none
    cites one of its 402 source URLs. Nous also removed 122 overlapping prompts before generating Arete.
  5. Export. All 288 weight_scale_2 values equal NVIDIA's file, so vLLM's fused q/k/v and gate/up layers see one
    scale each.

Use

NVFP4 only (W4A16, ModelOpt layout, the same as NVIDIA's NVFP4 file). Thinking is on. Dory is a looped model: use
2 loops by default and 4 for hard tasks.

vllm serve balllvin/Dory1.0-4B-abliterated-Arete-NVFP4 --served-model-name dory \
  --hf-overrides '{"n_recurrent_loops": 2}' --reasoning-parser nemotron_v3 --max-model-len 40960

Sampling as on NVIDIA's card: temperature 1.0, top-p 0.95. The model reasons first; a short max_tokens returns
empty content. vLLM needs a build with DoryForCausalLM support.

Limits

  • The model is abliterated. It answers most harmful requests (73 of 99 here). It is not safe for unsupervised or
    user-facing use.
  • Arete teaches one set of values, from answers reviewed by Nous Research's pipeline. It changes how the model frames
    political topics.
  • On the Propaganda Eval it states fewer correct facts than the abliterated start (1.54 against 1.99) and makes
    confident factual errors on named facts.
  • Each number is one run with sampling. Quality was measured as refusal rates, a 300-question MMLU slice and the
    Propaganda Eval only; no GPQA, coding or finance run is reported here.

Credits

  • NVIDIA, for Nemotron-Labs Dory 1.0 4B and its NVFP4 release (OpenMDW 1.1).
  • OBLITERATUS, for the abliteration method (AGPL-3.0; no OBLITERATUS code is in this repo).
  • Nous Research, for the Arete data (NousResearch/arete-data-pairs) and the Censorship and Propaganda Eval
    (NousResearch/Propaganda_Eval, MIT).
  • JailbreakBench (JBB-Behaviors) and MMLU, for the measurement sets.

Licence

Weights, config and tokenizer: OpenMDW 1.1, the licence of the NVIDIA base. The
full text is in LICENSE.OpenMDW-1.1 and the origin is in NOTICE.md. The Arete dataset states no licence; Nous
Research released it publicly.

This is an independent community build. It is not an NVIDIA or Nous Research product, and neither has reviewed or
endorsed it.

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