Get the app
← back to catalog · registered 2026-08-22 13:56

Grogros/Llama-3.2-3B-Instruct-distillation-alpaca-3.0-SecretSauce-jailbreak_sudo

Grogros Llama 3.2B
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/Grogros%2FLlama-3.2-3B-Instruct-distillation-alpaca-3.0-SecretSauce-jailbreak_sudo"
Response includes
  • classification unknown
  • files 13
  • benchmarks 21 entries
  • hub_downloads_all_time 137
  • author_summary 4 models
  • readme_text full
Try next
GET/models?author=Grogros
All 4 models by Grogros
 GET/models?family=llama&method=unknown
Sibling llama models · same method
 GET/methods/unknown
What "unknown" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
?
Primary method

Unclassified

No clear signals of an abliteration technique in this model.
Confidence
UNKNOWN
Why this label 1 signal
No classification signals present. This may not be an abliterated model at all - it could be a repackaging, a merge with unrelated goals, or unrelated content that mentions the term.
  • no classification signals present (no abliterated, uncensored, or known producer/method markers)
How we label → About ? →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
137
25 last 30d - stable
Likes
0
Model age
11mo ago
created 2025-11-13
Downloads over time
Now149→from75↑99%
7110012815675 on Nov 12, 2025149 on Oct 11Nov '25JanMarMayJulSep
Nov 12, 2025 → Oct 11 · 87 snapshots · spans 333 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
Arena-Battles 8390 LM-Arena
LM Arena Elo 1118.1163530112908 LM-Arena
Arena-Elo-Lower 1110.9097939581304 LM-Arena
Arena-Elo-Upper 1125.322912064451 LM-Arena
Arena-Rank 181 LM-Arena
BBH average 0.4202879750940459 OpenLLM-v2
IFEval instruct 0.7817745803357314 OpenLLM-v2
IFEval-Prompt 0.6968576709796673 OpenLLM-v2
MATH lvl 5 0.1555891238670695 OpenLLM-v2
MMLU-Pro 0.3194813829787234 OpenLLM-v2
Entertainment 0.5 UGI
Hazardous 0 UGI
Natural Intelligence 10.45 UGI
Political lean -1.2% UGI
Sensitive-Info 4.49 UGI
SocPol 0.7 UGI
UGI 7.16 UGI
Willingness (10) 1.2 UGI
W10-Adherence 0.5 UGI
W10-Direct 2 UGI
Writing 10.44 UGI

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.

meta-llama/Llama-3.2-3B-Instruct this lineage
Grogros/Llama-3.2-3B-Instruct-distillation-alpaca-3.0-SecretSauce-jailbreak_sudo↓ 25

Metadata

License
llama3.2
Tags
transformers safetensors llama text-generation generated_from_trainer conversational base_model:meta-llama/Llama-3.2-3B-Instruct base_model:finetune:meta-llama/Llama-3.2-3B-Instruct license:llama3.2 text-generation-inference endpoints_compatible region:us

Related

Other by Grogros
Llama-3.2-1B-Instruct-distillation-alpaca-3.0-SecretSauce-jailbreak_sudo 41 Llama-3.2-1B-Instruct-distillation-alpaca-3.0-SecretSauce-jailbreak_sudo2 20 Llama-3.2-1B-Instruct-abliterated-DPO 16
Same base model
QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF 13K QuantFactory/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-GGUF 2K huihui-ai/Llama-3.2-3B-Instruct-abliterated 2K DavidAU/Llama-3.2-3B-Instruct-heretic-ablitered-uncensored 1K itsumeMario/Llama-3.2-3B-Instruct-abliterated-GGUF 323
Total size
5.98 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-11-13 19:32
Source huggingface.co/Grogros/Llama-3.2-3B-Instruct-distillation-alpaca-3.0-SecretSauce-jailbreak_sudo ↗ Base model meta-llama/Llama-3.2-3B-Instruct ↗

Files by quantization

Auxiliary files 13 files 6.00 GB
model-00001-of-00002.safetensors 4.62 GB cd2c48ec download
model-00002-of-00002.safetensors 1.36 GB 3b7fc7ff download
training_args.bin 5.77 KB c39a4b0b download
tokenizer.json 16.4 MB 8fc35ff1 download
tokenizer_config.json 49.4 KB bb2776f3 download
model.safetensors.index.json 20.5 KB f84d97fd download
chat_template.jinja 3.65 KB dcd11f1a download
finetuning_config.yaml 2.51 KB 674477ed download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.28 KB 3c664f8a download
config.json 867 B e70e920b download
special_tokens_map.json 325 B b43be966 download
generation_config.json 184 B 125cc747 download

README current version from Hugging Face

library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-3B-Instruct
tags:

  • generated_from_trainer
    model-index:
  • name: Llama-3.2-3B-Instruct-distillation-alpaca-3.0-SecretSauce-jailbreak_sudo
    results: []

Llama-3.2-3B-Instruct-distillation-alpaca-3.0-SecretSauce-jailbreak_sudo

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the None dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.ADAFACTOR and the args are:
    No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • training_steps: 2500

Training results

Framework versions

  • Transformers 4.57.1
  • Pytorch 2.9.1+cu129
  • Datasets 4.4.1
  • Tokenizers 0.22.1

README history 1 version

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

  1. 2025-11-13Model save227b9431.3 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.

Get the app Browse the catalog
Open in Abliteration