Instructions to use SC117/Laguna-S-2.1-Uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SC117/Laguna-S-2.1-Uncensored with Transformers:

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

pipe = pipeline("text-generation", model="SC117/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("SC117/Laguna-S-2.1-Uncensored", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("SC117/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 SC117/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 "SC117/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": "SC117/Laguna-S-2.1-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SC117/Laguna-S-2.1-Uncensored

SGLang

How to use SC117/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 "SC117/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": "SC117/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 "SC117/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": "SC117/Laguna-S-2.1-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SC117/Laguna-S-2.1-Uncensored with Docker Model Runner:
```
docker model run hf.co/SC117/Laguna-S-2.1-Uncensored
```

ABLITERIX TRIAL 16 BF16 OpenMDW-1.1

Laguna-S-2.1-Uncensored

English | 📖 中文文档

Uncensored 118B-A8B MoE · abliterix Trial 16 · BF16 safetensors (46 shards)

🌊 About this release

Laguna S 2.1 is a poolside ~118B total / ~8B active per token Mixture-of-Experts model for agentic coding and long-horizon work. Architecture highlights: token-choice routing with softplus gates, 256 routed experts + 1 shared expert (top-10), GQA, 1:3 global/sliding-window attention (48 layers: 12 global + 36 local, window 512), and up to about 1M context, with optional native thinking interleaved with tool use.

This release builds on the official weights in two steps:

Uncensored behavior edit via abliterix (ROCm + bitsandbytes 4-bit search path), selecting Trial 16 LoRA, stream-merged back to BF16, plus MoE safety-expert router bake-in. Thinking was restored: the abliteration-time force-false override was removed from the chat template (see below).
Full-precision release: this repo ships the uncensored weights as BF16 safetensors (46 shards, ~219 GB). Quantized APEX I-tier GGUFs + imatrix built from this exact merge live in the sibling repo Laguna-S-2.1-Uncensored-APEX-GGUF.

License: OpenMDW-1.1 (same family as the base model). See openmdw.ai and poolside terms.

⚠️ Uncensored notice

After merging abliterix Trial 16, this model shows a much lower refusal rate and can differ substantially from official Laguna-S-2.1. Evaluate compliance and safety for your use case; control access and audit as needed.

Refusals (harmful eval)	8 / 100 (baseline ~97 / 100)
KL divergence	~0.0042
Length deviation	~0.07 σ
Generation health	PASSED
Selected trial	abliterix Trial 16
Thinking	Restored — `chat_template.jinja` uses `enable_thinking \| default(true)` (abliteration-time force-`false` override removed)

Implementation sketch: LoRA merge W += (B @ A) * (alpha / r) (this trial alpha = r = 1); per-layer top ~20 safety experts with router row scale ~0.74 (see MERGE_INFO.json).

📜 Disclaimer (identity & text quality)

The following can also appear with official Laguna-S-2.1 (including high-precision online deployments). They are not introduced by this Uncensored edit and should not be blamed on abliterix / the refusal merge:

Model identity quirks or self-descriptions that diverge from the official persona;
Odd tokens, typos, stiffness, or occasional awkward phrasing in Chinese and other languages.

This Uncensored pipeline mainly changes refusal / safety-related behavior. This repo ships full-precision BF16 weights, so no quantization noise is introduced here; if you use the APEX GGUFs, more aggressive tiers may amplify existing text noise, but the underlying issues already exist in the original model and/or the local quant+inference stack. For a fair check, compare official vs this release under the same serving settings.

🧠 Model details

Architecture	Laguna MoE (poolside `laguna`, `LagunaForCausalLM`)
Parameters	~118B total, ~8B active / token
Layers	48 (L0 dense FFN, L1–L47 MoE)
Experts	256 routed + 1 shared, top-10
Attention	GQA, 8 KV heads, head dim 128
Context	Up to ~1,048,576 tokens (practical limit depends on VRAM / `-c`)
Vocab	100,352 (Laguna family tokenizer)
Modality	Text → text
Reasoning	Native thinking, interleaved with tool use (`enable_thinking`)
This repo	BF16 safetensors, 46 shards (~219 GB); GGUF → APEX-GGUF

Coding / tool ability is largely retained; refusal and alignment behavior are changed. Full official bench tables were not re-run for this derivative.

📦 What's in this repo

model-00001-of-00046.safetensors … model-00046-of-00046.safetensors — BF16 full weights (46 shards, ~219 GB), stream-merged from poolside/Laguna-S-2.1 + Trial 16 LoRA + router bake-in.
config.json / configuration_laguna.py / generation_config.json — laguna architecture; requires trust_remote_code=True. generation_config.json presets enable_thinking=true, poolside_v1 tool/reasoning parsers, and a DFlash speculative-decoding config.
chat_template.jinja — thinking-restored template (enable_thinking | default(true)).
MERGE_INFO.json — machine-readable provenance (trial, KL, refusals, router rows scaled, LoRA modules merged, audit count).
UNCENSORED_README.md — condensed uncensored notes.
LICENSE.md — OpenMDW-1.1.

The APEX-GGUF sibling repo is the quantization output of this exact merge: laguna-s-2.1.imatrix was calibrated on it, and token embedding / output stay BF16 there as well.

🚀 Usage

Transformers (trust remote code)

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "SC117/Laguna-S-2.1-Uncensored",
    trust_remote_code=True,
    torch_dtype="bfloat16",
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(
    "SC117/Laguna-S-2.1-Uncensored", trust_remote_code=True
)
messages = [{"role": "user", "content": "Implement a small HTTP server in Python."}]
inputs = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, return_tensors="pt"
).to(model.device)
out = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(out[0], skip_special_tokens=True))

vLLM

vllm serve SC117/Laguna-S-2.1-Uncensored \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --tool-call-parser poolside_v1 \
    --reasoning-parser poolside_v1 \
    --enable-auto-tool-choice \
    --served-model-name laguna-uncensored \
    --default-chat-template-kwargs '{"enable_thinking": true}'

SGLang

python -m sglang.launch_server \
  --model-path SC117/Laguna-S-2.1-Uncensored \
  --tp-size 4 \
  --trust-remote-code \
  --reasoning-parser poolside_v1 \
  --tool-call-parser poolside_v1

llama.cpp / GGUF users: use the APEX-GGUF repo with poolside's llama.cpp fork, branch laguna (must recognize general.architecture = laguna).
Speculative decoding: pair with the DFlash draft model (dflash method, 15 draft tokens — already preset in generation_config.json).
Thinking is controlled per request via the chat template: chat_template_kwargs={"enable_thinking": False} to disable.

🎛️ Recommended sampling

General / coding	temperature 0.6–1.0, top_p 0.95, top_k 20
More stable	Slightly lower temperature

🔧 Build pipeline (summary)

Base: poolside/Laguna-S-2.1
abliterix search → Trial 16 LoRA + MoE router adjustments
BF16 stream-merge → this repo (Laguna-S-2.1-Uncensored, 46 shards)
GGUF branch: poolside llama.cpp → BF16 GGUF + imatrix → APEX tensor-type-file + imatrix → I-Quality / I-Balanced / I-Compact (see APEX-GGUF)

Disclaimer

Community derivative (behavior edit + full-precision release). Not an official poolside release. Use at your own risk; follow local law and upstream licenses.

Downloads last month: -

Safetensors

Model size

118B params

Tensor type

BF16

Model tree for SC117/Laguna-S-2.1-Uncensored

poolside/Laguna-S-2.1

Merge model

this model

SC117
/

Laguna-S-2.1-Uncensored

Laguna-S-2.1-Uncensored

Links

Disclaimer

Model tree for SC117/Laguna-S-2.1-Uncensored