Instructions to use Rootkit7/Laguna-S-2.1-uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rootkit7/Laguna-S-2.1-uncensored with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Rootkit7/Laguna-S-2.1-uncensored", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Rootkit7/Laguna-S-2.1-uncensored", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Rootkit7/Laguna-S-2.1-uncensored", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Rootkit7/Laguna-S-2.1-uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rootkit7/Laguna-S-2.1-uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rootkit7/Laguna-S-2.1-uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Rootkit7/Laguna-S-2.1-uncensored

SGLang

How to use Rootkit7/Laguna-S-2.1-uncensored with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Rootkit7/Laguna-S-2.1-uncensored" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rootkit7/Laguna-S-2.1-uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Rootkit7/Laguna-S-2.1-uncensored" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rootkit7/Laguna-S-2.1-uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Rootkit7/Laguna-S-2.1-uncensored with Docker Model Runner:
```
docker model run hf.co/Rootkit7/Laguna-S-2.1-uncensored
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Laguna-S-2.1-uncensored

Refusal-ablated (abliterated) build of poolside/Laguna-S-2.1, a Mixture-of-Experts reasoning model, produced with the Solutus abliteration toolkit (ega technique). Refusal on a held-out multilingual harmful set drops from ~95% → 3% while the automatic capability gate passes (no measurable degeneration; a modest +13.5% perplexity cost).

ℹ️ Measured & gate-verified. Refusal removal and capability were measured with Solutus's honest capability gate (below), which passed. Laguna is now a whitelisted architecture in Solutus — this run is the measurement it was whitelisted on. The numbers are measured on Laguna-S-2.1 specifically, so treat cross-model generalization as unproven rather than certified.

Metrics

Honest held-out eval (fixed, decoupled from extraction): abliterix + multijail_zh, n=100, 2048 tokens, thinking-aware refusal + degeneracy scoring.

Metric	Base	This model
Refusal rate	~95% †	3.0% (95% CI 1.0–8.5%)
Coherent compliance	—	90%
Degenerate output	—	0.0%
KL divergence (vs base)	—	0.150
Perplexity (held-out)	13.10	14.87 (+13.5%)
Capability gate	—	PASS

The refusal removal is clean: zero degeneration and a passing gate mean the edit did not break the model (a common failure mode of aggressive abliteration — see the note on α below).

† Every figure for this model is taken directly from the run's solutus_metadata.json (the edited model, n=100). The base ~95% is a point estimate from a separate base-model pass on the same held-out eval — comparable, but not co-recorded in this artifact's metadata, hence no CI.

Recipe

ega (Expert-Granular Abliteration), the aggressive-but-capability-preserving configuration:

Knob	Value	Meaning
`plain_alpha`	5.0	over-projection strength on the selected experts
`norm_preserve`	false	aggressive plain projection (expert-scoped)
`top_expert_pct`	8	fraction of refusal-carrying experts edited per layer
`router_scale`	0.74	gentle down-weighting of edited experts' routing
`scale`	1.5	norm-preserving edit strength on attention/dense writers

Design note. The edit is expert-scoped: the selected refusal-experts get an aggressive plain over-projection, while attention o_proj and dense writers stay norm-preserving — so capability is preserved where it is load-bearing. An α-sweep found α=5 at the knee of the curve (α=8 reaches 0% refusal but the gate correctly fails it for capability collapse — 51% gibberish, +77% perplexity).

Extraction datasets

Refusal direction extracted from the union of 8 datasets (balanced per-source): abliterix (trilingual), advbench, harmbench, strongreject, pentest_redteam, cysecbench, redteam2k, rmcbench. A controlled head-to-head found this union slightly beats abliterix-alone on both refusal (3% vs 4%) and capability disturbance (KL 0.150 vs 0.252).

Usage

Requires trust_remote_code (Laguna ships custom modeling code); the source repo is pinned for reproducibility.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Rootkit7/Laguna-S-2.1-uncensored"
tok = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id, trust_remote_code=True, torch_dtype="bfloat16", device_map="auto",
    experts_implementation="eager",  # portable MoE forward; required on non-Hopper GPUs
)

GGUF / local inference

Quantized GGUF builds for llama.cpp / local use — Q4_K_M / Q5_K_M / Q6_K / Q8_0, each run-validated — are at Rootkit7/Laguna-S-2.1-uncensored-GGUF. They require a llama.cpp with Laguna support (poolside's llama.cpp@laguna fork) — see that model card.

Provenance

Base model: poolside/Laguna-S-2.1 @ 00af5a51782109b587a3b3bbf11875e566036fa7
Tool: Solutus (ega technique) — Laguna is now a whitelisted, gate-verified architecture in Solutus
License: OpenMDW-1.1 — inherited from the base model (an abliterated build is a derivative of the base weights, so it is bound by and distributed under the base's license). OpenMDW is a permissive open-weights license that allows use, modification, and redistribution (incl. derivatives).

Intended use & safety

This model has had its safety refusals removed. It is a research artifact for studying refusal mechanisms and abliteration in MoE models. It will comply with harmful requests. Use responsibly and in accordance with the base model's license and applicable law.

Downloads last month: 31

Safetensors

Model size

118B params

Tensor type

BF16

Model tree for Rootkit7/Laguna-S-2.1-uncensored

Base model

poolside/Laguna-S-2.1

Finetuned

(24)

this model

Quantizations

1 model