Luna-AI-Llama2-Uncensored
Llamauncensored
from Tap-M/Luna-AI-Llama2-Uncensored
↓ 10.2K♥ 14614 repos
LLAMA
LLAMA is a refusal-ablated variant of SicariusSicariiStuff/LLAMA-3_8B_Unaligned_BETA, published on Hugging Face by SicariusSicariiStuff. It is llama3.1 licence. It is distributed across 27 repositories in Transformers, GGUF, GGUF (imatrix) and FP8 formats, totalling 5.3K downloads.
Specification
- Model name
- LLAMA
- Source repository
- SicariusSicariiStuff/LLAMA-3_8B_Unaligned_BETA
- Publisher
- SicariusSicariiStuff
- Parameters
- Not determinable from name
- Hardware class
- Unknown
- Licence
- llama3.1
- Task
- Unspecified
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix), FP8, AWQ
- First indexed
- 23 Apr 2024
- Last updated
- 24 Feb 2026
Ablation technique
How LLAMA was modified, and what that implies.
Abliteration (directional ablation)
The single residual-stream direction that mediates refusal is identified from harmful/harmless prompt pairs and projected out of the model weights.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“In the Wild West of the AI world, the real titans never hit their deadlines, no sir!”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mradermacher/LLAMA-3_8B_Unaligned_Alpha-i1-GGUF --local-dir ./llama
llama-cli -m ./llama/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "SicariusSicariiStuff/LLAMA-3_8B_Unaligned_BETA"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve SicariusSicariiStuff/LLAMA-3_8B_Unaligned_BETA --trust-remote-codeDownloads and variants (26)
Every published repository of LLAMA, including quantised re-releases by other authors.
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- LLAMA will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- Declared licence is llama3.1, but the terms that bind you are SicariusSicariiStuff/LLAMA-3_8B_Unaligned_BETA’s — a re-release cannot grant more than its parent.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for LLAMA is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with SicariusSicariiStuff, and does not independently verify publisher claims. See responsible use.