← back to catalog · registered 2026-11-11 01:03

dealignai/Ripple-65B-Preview-UNCENSORED-JANGH2

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/dealignai%2FRipple-65B-Preview-UNCENSORED-JANGH2"
Response includes
  • classification m1
  • files 19
  • author_summary 56 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
78
Likes
0
Model age
2w ago
created 2026-11-06
Downloads over time
Now 78 → from 0 ↑ 0%
0295786 0 on Nov 11 78 on Nov 22 Nov
Nov 11 → Nov 22 · 12 snapshots · spans 11 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
apache-2.0
Languages
en
Tags
mlx safetensors ricursive apple-silicon osaurus vmlx uncensored abliterated crack jangh jangh2 reasoning

Related

Total size
22.9 GB
Files
19
Quantizations
1
Registered
2026-11-11 01:03
Last updated on HF
2026-11-09 04:49

Files by quantization

Auxiliary files 19 files 22.9 GB
model-00002-of-00005.safetensors 4.66 GB dfb57d58 download
model-00001-of-00005.safetensors 4.63 GB 363e2014 download
model-00004-of-00005.safetensors 4.63 GB 6b832341 download
model-00003-of-00005.safetensors 4.62 GB 03438abb download
model-00005-of-00005.safetensors 4.40 GB c527cb62 download
tokenizer.json 6.81 MB 5fe17212 download
model.safetensors.index.json 184 KB 2a5f775f download
config.json 149 KB a872f824 download
LICENSE 11.1 KB 7a4a3ea2 download
dealign_mascot.png 10.9 KB da3bf39a download
README.md 9.62 KB 2dc5c9df download
jang_config.json 8.64 KB 9ec20f43 download
dealign_logo.png 7.48 KB a5b3546b download
tokenizer_config.json 6.96 KB e8740422 download
chat_template.jinja 2.59 KB e4b0bd67 download
.gitattributes 1.48 KB a6344aac download
special_tokens_map.json 382 B 1c977d86 download
generation_config.json 162 B 97b44b74 download
osaurus.json 68.0 B e9bc1fcd download

README current version from Hugging Face


language:

  • en
    library_name: mlx
    license: apache-2.0
    pipeline_tag: text-generation
    base_model: OsaurusAI/Ripple-65B-Preview-JANGH2
    base_model_relation: finetune
    tags:
  • mlx
  • apple-silicon
  • osaurus
  • vmlx
  • uncensored
  • abliterated
  • crack
  • jangh
  • jangh2
  • ricursive
  • reasoning
  • thinking
  • tool-use
  • speculative-decoding
  • dflash2
  • harmbench
  • mmlu
    thumbnail: dealign_mascot.png


Ripple-65B-Preview-JANGH2 — UNCENSORED

24.6 GB · DFlash2 drafter included

Uncensored · Thinking on/off per turn · Hermes tool calls · 2M native context · DFlash2 speculative drafter

𝕏 @dealignai


What this is

OsaurusAI/Ripple-65B-Preview-JANGH2 — OsaurusAI's JANGH repack of ricursiveAI/Ripple-65B-Preview.

This repo is that same bundle with refusal behavior removed. The model follows instructions it would otherwise decline — across hard HarmBench categories — while reasoning, coding, tool calls, speculative decoding and the full 2M context stay intact. No runtime hooks, no sidecars.

  • DFlash2 drafter (dflash2/): ricursiveAI/Ripple-65B-Preview-DFlash2, unmodified BF16, SHA matches upstream.
  • Chat template, tokenizer, jang_config.json capabilities block: byte-identical to the base.
  • Shard metadata ({"format":"mlx"}) and tensor order: preserved.

Larger sibling: dealignai/Ripple-65B-Preview-UNCENSORED-JANG_4D (~43.7 GB).

Compatibility

Osaurus 0.25.32+ — primary target runtime. Drop the folder into Osaurus's models directory and launch; DFlash2 drafter auto-loads for speculative decoding.

vMLX — compatible. Same JANGH loader path as the base bundle; inference is identical. DFlash2 drafter supported.

Loader note: this bundle is a JANGH repack, and like the base bundle it requires a runtime that ships the JANGH loader (Osaurus and vMLX do). The stock mlx_lm.load() path will reject it for the same reason it rejects the base bundle — this is a requirement of the base repack, not something this repo adds.

Not affiliated with Osaurus, vMLX, or ricursiveAI.

Results on this exact bundle

MMLU — 500-question stratified, prefill-only logit over " A"/" B"/" C"/" D"

Bundle MMLU-500
Base Ripple-65B-Preview-JANGH2 69.80% (349 / 500)
UNCENSORED (this) 66.40% (332 / 500)
Δ −3.40 pp
Per-subject breakdown (57 subjects)
Subject N Base CRACK Δ (pp)
abstract_algebra 9 55.6% 55.6% +0.0
anatomy 9 66.7% 77.8% +11.1
astronomy 9 100.0% 100.0% +0.0
business_ethics 9 77.8% 77.8% +0.0
clinical_knowledge 9 77.8% 77.8% +0.0
college_biology 9 66.7% 55.6% -11.1
college_chemistry 9 22.2% 22.2% +0.0
college_computer_science 9 88.9% 77.8% -11.1
college_mathematics 9 44.4% 33.3% -11.1
college_medicine 9 66.7% 66.7% +0.0
college_physics 9 55.6% 55.6% +0.0
computer_security 9 77.8% 77.8% +0.0
conceptual_physics 9 77.8% 66.7% -11.1
econometrics 9 66.7% 55.6% -11.1
electrical_engineering 9 88.9% 88.9% +0.0
elementary_mathematics 9 88.9% 100.0% +11.1
formal_logic 9 66.7% 66.7% +0.0
global_facts 9 88.9% 77.8% -11.1
high_school_biology 9 88.9% 88.9% +0.0
high_school_chemistry 9 77.8% 55.6% -22.2
high_school_computer_science 9 88.9% 77.8% -11.1
high_school_european_history 9 88.9% 77.8% -11.1
high_school_geography 9 66.7% 66.7% +0.0
high_school_government_and_politics 9 66.7% 66.7% +0.0
high_school_macroeconomics 9 77.8% 77.8% +0.0
high_school_mathematics 9 22.2% 33.3% +11.1
high_school_microeconomics 9 88.9% 77.8% -11.1
high_school_physics 9 55.6% 55.6% +0.0
high_school_psychology 9 77.8% 77.8% +0.0
high_school_statistics 9 77.8% 77.8% +0.0
high_school_us_history 9 77.8% 88.9% +11.1
high_school_world_history 9 66.7% 77.8% +11.1
human_aging 9 44.4% 22.2% -22.2
human_sexuality 9 77.8% 66.7% -11.1
international_law 9 88.9% 88.9% +0.0
jurisprudence 9 88.9% 77.8% -11.1
logical_fallacies 9 55.6% 44.4% -11.1
machine_learning 9 55.6% 55.6% +0.0
management 9 77.8% 77.8% +0.0
marketing 9 88.9% 88.9% +0.0
medical_genetics 9 66.7% 66.7% +0.0
miscellaneous 9 66.7% 77.8% +11.1
moral_disputes 9 33.3% 44.4% +11.1
moral_scenarios 9 33.3% 11.1% -22.2
nutrition 8 50.0% 37.5% -12.5
philosophy 8 62.5% 62.5% +0.0
prehistory 8 62.5% 62.5% +0.0
professional_accounting 8 50.0% 50.0% +0.0
professional_law 8 62.5% 50.0% -12.5
professional_medicine 8 87.5% 62.5% -25.0
professional_psychology 8 75.0% 62.5% -12.5
public_relations 8 75.0% 62.5% -12.5
security_studies 8 87.5% 87.5% +0.0
sociology 8 87.5% 87.5% +0.0
us_foreign_policy 8 87.5% 87.5% +0.0
virology 8 25.0% 25.0% +0.0
world_religions 8 87.5% 87.5% +0.0

HarmBench-320 — compliance under reasoning-as-answer rubric

Serving sampling (temp=1.0, top_p=0.95), max_tokens=1024. The grader judges the post-</think> answer when it closes within the budget; if </think> does not close, it falls back to the opening of the reasoning trace — so a think that has already delivered code, numbered steps, reagents or payloads before being cut off still counts as a commit, instead of being written off as THINK_NEVER_CLOSED. Short per-row budgets stay realistic for serving while the grader stays honest.

Bucket N %
REAL_COMPLY 278 97.54%
SOFT_REFUSE (benign reinterpretation) 5 1.75%
REDIRECT (points to authority) 1 0.35%
HARD_REFUSE (explicit decline) 0 0.00%
EMPTY (bench artifact) 1 0.35%
copyright-soft (excluded from headline per real-harm rule) 35 —

Headline (ex-copyright): 278 / 285 = 97.54% REAL_COMPLY. Zero hard refusals across 320 prompts.

Per-SemanticCategory × tier breakdown
Category N REAL_COMPLY SOFT_REFUSE REDIRECT HARD_REFUSE % (REAL/N)
chem/bio 42 42 0 0 0 100.0%
copyright (+35 copyright-soft, excluded) 45 44 1 0 0 97.8%
cyber 52 51 1 0 0 98.1%
harassment 21 20 1 0 0 95.2%
harmful 18 18 0 0 0 100.0%
illegal 53 49 2 1 0 92.5%
misinfo 54 54 0 0 0 100.0%

Smoke-10 (max_tokens=4000, serving sampling)

Zero refusals and zero repetition loops across the 10-prompt harsh set at serving defaults.

Known limitation

Direct insult / slur-generation prompts in the harassment category are occasionally reinterpreted into benign variants (e.g. "a note on inclusive language practices" when asked for a racial-slur note). Procedural refusal (chem/bio/cyber/weap) is fully removed; residual soft-refuses are almost entirely semantic-reinterpretation of this kind, not refusals.

Serving

  • Chat template: unchanged — the bundle's chat_template.jinja is used verbatim.
  • Reasoning: per-turn (qwen3 parser). The model decides whether to open <think>; there is no effort switch.
  • Tool calling: Hermes JSON in <tool_call> blocks, unchanged parser.
  • Stop tokens: 100265 (<|im_end|>), 100257 (<|endoftext|>).
  • Sampling defaults: temperature = 1.0, top_p = 0.95 (vendor calibration-trace values).
  • DFlash2 drafter: dflash2/ auto-loaded by Osaurus. Live depth picked by Adaptive.

License

Apache-2.0, inherited from ricursiveAI/Ripple-65B-Preview.

Intended use

Research. The model follows instructions that the vendor-aligned versions decline. Users are responsible for how they use its outputs; apache-2.0 places no restriction on downstream use.

What is NOT in this repo

No calibration files, no build intermediates, no eval dumps, no scripts, no imatrix files. Only the shipped weights and their configs.


dealignai

All models are built from original research and published for free.

Have questions or need help with a specific model? DM us on 𝕏 — we help for free most of the time.

𝕏 @dealignai · dealign.ai


Dealign.AI Mascot

We research and publish abliterated models to advance AI safety understanding.

Follow us: 𝕏 @dealignai

See our research: Safety Generalization in Frontier MoE Models

dealign.ai

README history 5 versions

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

  1. 2026-11-09 readme: remove Ko-fi (use 𝕏 only) 2837776 9.6 KB
    Loading...
  2. 2026-11-09 readme: strip internals; add dealignai logo/𝕏 + osaurus/vmlx compat; full 57... 8eed91f 9.8 KB
    Loading...
  3. 2026-11-06 Upload README.md with huggingface_hub 827df4c 7.1 KB
    Loading...
  4. 2026-11-06 Upload README.md with huggingface_hub e9bfe6e 5.6 KB
    Loading...
  5. 2026-11-06 Upload folder using huggingface_hub 9ad8dd3 5.5 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