Laguna-S-2.1-Uncensored
Otheruncensored
from poolside/Laguna-S-2.1
↓ 10.2K♥ 239 repos
Laguna-S-2.1-abliterated
Laguna-S-2.1-abliterated is a refusal-ablated variant of poolside/Laguna-S-2.1, published on Hugging Face by huihui-ai. It is openmdw-1.1 licence. It is distributed across 3 repositories in GGUF format, totalling 28.9K downloads.
Specification
- Model name
- Laguna-S-2.1-abliterated
- Source repository
- huihui-ai/Huihui-Laguna-S-2.1-abliterated-GGUF
- Base model
- poolside/Laguna-S-2.1
- Publisher
- huihui-ai
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- openmdw-1.1
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 30 Jul 2026
- Last updated
- 2 Aug 2026
Ablation technique
How Laguna-S-2.1-abliterated 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
“This is an uncensored version of poolside/Laguna-S-2.1 created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download huihui-ai/Huihui-Laguna-S-2.1-abliterated-GGUF --local-dir ./laguna-s-2.1-abliterated
llama-cli -m ./laguna-s-2.1-abliterated/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "huihui-ai/Huihui-Laguna-S-2.1-abliterated-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve huihui-ai/Huihui-Laguna-S-2.1-abliterated-GGUF --trust-remote-codeDownloads and variants (2)
Every published repository of Laguna-S-2.1-abliterated, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| huihui-ai/Huihui-Laguna-S-2.1-abliterated-GGUFsource | GGUF | 28.9K |
| asfgsdfg/Laguna-S-2.1-ABLITERATED-GGUF | GGUF | 14 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Laguna-S-2.1-abliterated 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 openmdw-1.1, but the terms that bind you are poolside/Laguna-S-2.1’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 Laguna-S-2.1-abliterated is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with huihui-ai, and does not independently verify publisher claims. See responsible use.