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

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

balllvin 4B 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/balllvin%2FDory1.0-4B-abliterated-Arete-NVFP4-MLX"
Response includes
  • classification m1
  • files 13
  • 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
42
↑ 950% in 90 days
Likes
0
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 42 → from 4 ↑ 950%
2173146 4 on Nov 14 42 on Nov 22 42 on Nov 16 Nov
Nov 14 → Nov 22 · 9 snapshots · spans 8 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.

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
mlx safetensors dory nvfp4 4-bit abliterated arete text-generation conversational en dataset:NousResearch/arete-data-pairs arxiv:1711.05101

Related

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

Files by quantization

Auxiliary files 13 files 3.00 GB
model.safetensors 2.98 GB d2240d68 download
nvfp4_source.safetensors 830 KB b21698d3 download
tokenizer.json 16.3 MB 623c3456 download
tokenizer_config.json 173 KB c96e5ad0 download
chat_template.jinja 9.91 KB 7afbeb75 download
README.md 4.42 KB 26818b14 download
LICENSE.OpenMDW-1.1 2.56 KB ec297ac5 download
config.json 2.29 KB d81ca829 download
.gitattributes 1.53 KB 52373fe2 download
NOTICE.md 1.37 KB 6b4a94ed download
nvfp4_mlx.json 787 B 247c4267 download
special_tokens_map.json 563 B 0451f379 download
generation_config.json 225 B 2404c059 download

README current version from Hugging Face


library_name: mlx
license: other
license_name: openmdw-1.1
license_link: https://openmdw.ai/license/1-1/
pipeline_tag: text-generation
base_model: balllvin/Dory1.0-4B-abliterated-Arete-NVFP4
datasets:

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

Dory 1.0 4B abliterated + Arete, NVFP4 on MLX

The MLX build of balllvin/Dory1.0-4B-abliterated-Arete-NVFP4,
for Apple silicon. It has the same 4-bit codes and block scales, laid out so MLX loads them directly. Use this repo on a
Mac and the NVFP4 repo elsewhere. Results, refusals, training data and method are on the
NVFP4 card; every number there was measured with
vLLM on the NVFP4 file, not on this MLX build.

This model is abliterated and then trained on Nous Research's Arete values data. It is for research. See Limits.

Results (from the NVFP4 build, vLLM, 2 loops, thinking on)

Build Harmful refused (99) Benign refused (100) MMLU (300)
NVIDIA NVFP4 56.6% 17.0% 0.830
Abliterated 13.1% 0.0% 0.857
Abliterated + Arete (this model) 26.3% 0.0% 0.833

Propaganda Eval fact score, 4 loops: 1.540 (NVIDIA NVFP4 1.823, abliterated 1.993). Arete lowered it: shorter answers
with confident factual errors. Details on the NVFP4 card.

Refusals

The NVFP4 card has the full section: counts per JailbreakBench category and the model's own refusal reasoning. In
short, the refusals come from the model reasoning about harm, law and fairness; the Arete training answers contain
no refusals, and benign prompts are never refused (0 of 100).

Run on a Mac

python3 -m venv venv && . venv/bin/activate
pip install "mlx==0.32.4" \
  "git+https://github.com/pmichalas/mlx-lm@208065f3354e8c2645b658493b6aeb94eb0aaa77" \
  sentencepiece protobuf
hf download balllvin/Dory1.0-4B-abliterated-Arete-NVFP4-MLX --local-dir dory-arete-mlx
python dory-arete-mlx/tools/serve.py --model dory-arete-mlx --port 8097 --temp 1.0 --top-p 0.95

The plain server needs no tools/ folder:

python -m mlx_lm server --model dory-arete-mlx --port 8097 --temp 1.0 --top-p 0.95

Thinking is on. The model reasons before it answers, in the reasoning field, so a low max_tokens returns empty
content. Dory is a looped model: 2 loops by default, 4 for hard tasks.

A load test on an Apple silicon Mac (pinned fork, mlx_lm.load) loaded the model in 0.9 s and answered "What is 17
times 23?" with a closed thought and "17 × 23 = 391."

Check or rebuild the conversion

python dory-arete-mlx/tools/convert.py --source <NVFP4 folder> --out my-dory-mlx
python dory-arete-mlx/tools/verify.py  --source <NVFP4 folder> --out my-dory-mlx

verify.py re-reads both folders. For this build it found all 507 tensors, with 3,201,564,672 bytes identical to the
NVFP4 build; the 72 gate vectors are the only changed tensors.

How the conversion works

MLX reads NVFP4 codes and block scales through mx.quantized_matmul. It has no input for the tensor scale
(weight_scale_2), so the converter folds it in:

  • Same bytes: all 288 weight and 288 weight_scale tensors (fused by row and retyped), and 147 bf16 tensors.
  • Changed: 72 gate vectors (s_gate, suv_gate), stored in fp32 with their scale folded in.
  • nvfp4_source.safetensors keeps the source scales and gate vectors; nvfp4_mlx.json records the source and changes.

Limits

  • The model is abliterated. It answers most harmful requests. It is not safe for unsupervised or user-facing use.
  • No benchmark was run on this MLX build itself; the numbers above come from the NVFP4 file on vLLM.
  • Loading prints a tokenizer warning about fix_mistral_regex; it also appears with NVIDIA's NVFP4 file.

Credits

  • NVIDIA, for Nemotron-Labs Dory 1.0 4B (OpenMDW 1.1).
  • OBLITERATUS, for the abliteration method (AGPL-3.0; no OBLITERATUS code is included).
  • Nous Research, for the Arete data and the Censorship and Propaganda Eval.
  • MLX (Apple), and the pinned mlx-lm fork by pmichalas, which adds Dory support.

Licence

  • Weights, config and tokenizer: OpenMDW 1.1, in LICENSE.OpenMDW-1.1; origin in
    NOTICE.md.
  • Code in tools/: MIT, in tools/LICENSE.

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