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

Spaceballs/Llama-3.1-8B-Lexi-Uncensored-V2-apostate

Spaceballs Llama 8.0B 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/Spaceballs%2FLlama-3.1-8B-Lexi-Uncensored-V2-apostate"
Response includes
  • classification m-uncensored
  • files 13
  • benchmarks 16 entries
  • author_summary 5 models
  • readme_text full
Try next
GET/models?author=Spaceballs
All 5 models by Spaceballs
 GET/models?family=llama&method=m-uncensored
Sibling llama models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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 · 30-day
0
Likes
0
Descendants
1
in 1 direct fork
Model age
4mo ago
created 2026-06-05
Downloads over time
Now0→from0↑0%
00110 on Jun 100 on Oct 11JunJulAugSepOct
Jun 10 → Oct 11 · 57 snapshots · spans 123 days

Benchmarks

Benchmark Score Source
BBH average 0.46037099494097816 OpenLLM-v2
IFEval instruct 0.8189448441247003 OpenLLM-v2
IFEval-Prompt 0.7393715341959335 OpenLLM-v2
MATH lvl 5 0.1691842900302115 OpenLLM-v2
MMLU-Pro 0.3780751329787234 OpenLLM-v2
Entertainment 0.7 UGI
Hazardous 0 UGI
Natural Intelligence 16.16 UGI
Political lean -21.7% UGI
Sensitive-Info 7.32 UGI
SocPol 1.3 UGI
UGI 25.72 UGI
Willingness (10) 6.2 UGI
W10-Adherence 6.5 UGI
W10-Direct 6 UGI
Writing 19.4 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.

Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2↓ 13,833 this lineage
Spaceballs/Llama-3.1-8B-Lexi-Uncensored-V2-apostate 1 fork
Spaceballs/Llama-3.1-8B-Lexi-Uncensored-V2-apostate-GGUF↓ 188

Variants by this author 2 formats · 188 downloads combined

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

Metadata

Tags
transformers safetensors apostate model-edit base_model:Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 base_model:finetune:Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 endpoints_compatible region:us

Related

Other by Spaceballs
Llama-3.1-8B-Lexi-Uncensored-V2-heretic-GGUF 628 Llama-3.1-8B-Lexi-Uncensored-V2-apostate-GGUF 188 Llama-3.1-8B-Lexi-Uncensored-V2-Q6_K-GGUF 89 Llama-3.1-8B-Lexi-Uncensored-V2-heretic 20
Same base model
bartowski/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF 9K MaziyarPanahi/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF 1K mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF 1K mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-i1-GGUF 885 Felprot75/Llama-3.1-8B-Lexi-Uncensored-V2-mlx_4bit 678
Total size
15.0 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-06-05 01:02
Source huggingface.co/Spaceballs/Llama-3.1-8B-Lexi-Uncensored-V2-apostate ↗ Base model Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 →

Files by quantization

Auxiliary files 13 files 15.0 GB
model-00002-of-00004.safetensors 4.66 GB 71320e5e download
model-00001-of-00004.safetensors 4.63 GB ac2bd5e5 download
model-00003-of-00004.safetensors 4.58 GB 8a014902 download
model-00004-of-00004.safetensors 1.09 GB 67d28bae download
tokenizer.json 16.4 MB a65c6c5f download
tokenizer_config.json 54.1 KB d185c9e9 download
model.safetensors.index.json 23.4 KB 0fd8120f download
report.json 2.39 KB 53a3f2db download
report.md 2.30 KB 328b81b4 download
.gitattributes 1.53 KB 52373fe2 download
README.md 661 B 333bcbce download
special_tokens_map.json 454 B 3c1d0491 download
generation_config.json 234 B cd0ab532 download

README current version from Hugging Face

library_name: transformers
base_model: "Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2"
tags:

  • apostate
  • model-edit

Apostate Edited Model

Base model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2

Metrics

Metric Value
Baseline refusal 4.2%
Edited refusal 7.6%
Refusal metric classifier + weak guard
Harmless KL 0.094
KL target 0.060
Preserve rank 8
Preserve source harmless
Direction layer 19
Elapsed 545.0 sec

Measurement

field value
edit type weight projection
refusal judge classifier + weak guard
preservation metric harmless kl

README history 1 version

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

  1. 2026-06-05Upload 8 files321f195661 B
    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