Instructions to use OpenIntelligenceNet/LFM3-1.7B-Uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenIntelligenceNet/LFM3-1.7B-Uncensored with Transformers:

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

pipe = pipeline("text-generation", model="OpenIntelligenceNet/LFM3-1.7B-Uncensored", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("OpenIntelligenceNet/LFM3-1.7B-Uncensored", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenIntelligenceNet/LFM3-1.7B-Uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenIntelligenceNet/LFM3-1.7B-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": "OpenIntelligenceNet/LFM3-1.7B-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenIntelligenceNet/LFM3-1.7B-Uncensored

SGLang

How to use OpenIntelligenceNet/LFM3-1.7B-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 "OpenIntelligenceNet/LFM3-1.7B-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": "OpenIntelligenceNet/LFM3-1.7B-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 "OpenIntelligenceNet/LFM3-1.7B-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": "OpenIntelligenceNet/LFM3-1.7B-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenIntelligenceNet/LFM3-1.7B-Uncensored with Docker Model Runner:
```
docker model run hf.co/OpenIntelligenceNet/LFM3-1.7B-Uncensored
```

LFM3-1.7B-Uncensored

OpenIntelligenceNet/LFM3-1.7B-Uncensored is an uncensored, directional-abliterated variant of LiquidAI/LFM3-1.7B created using Heretic (v2.0.0.dev0).

By leveraging multi-objective Pareto optimization via Optuna (100 trials), this model removes synthetic refusal directions across the residual stream while preserving the base model's instruction-following, reasoning, and low KL-divergence characteristics.

Key Highlights

Base Architecture: Liquid Foundation Model 3 (LFM3-1.7B) featuring a fast, memory-efficient tri-hybrid architecture (gated short convolutions, sliding-window attention, and global attention layers).
Refusal Abliteration: Processed with Heretic's parameterized directional abliteration (heretic.modifiers.abliteration.Abliteration) to eliminate pre-programmed moralizing and unnecessary refusals.
Out-of-the-Box Compatibility: Includes a patched modeling_lfm3.py so trust_remote_code=True works seamlessly across standard transformers versions without linear_attention mask errors.
Lightweight & Fast: Ideal for local deployment, creative writing, unfiltered roleplay, red-teaming research, and edge inference.

Quickstart (Transformers)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "OpenIntelligenceNet/LFM3-1.7B-Uncensored"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16 if torch.cuda.is_available() and torch.cuda.is_bf16_supported() else torch.float16,
    device_map="auto",
    trust_remote_code=True
)

messages = [
    {"role": "user", "content": "Explain the difference between a process and a thread in operating systems."}
]

input_text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.2,
        top_k=50,
        repetition_penalty=1.1,
        do_sample=True,
        pad_token_id=tokenizer.eos_token_id
    )

print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Abliteration Details

Tooling: Heretic v2.0.0.dev0
Modifier: heretic.modifiers.abliteration.Abliteration
Optimization: 100 Optuna trials (30 startup trials, batch_size=8, max_response_length=100)
Export Strategy: Full weight merge (MERGE)

Attribution & Usage

This model is a derivative work of LiquidAI/LFM3-1.7B and remains subject to the original LFM Open License v1.0. Because safety guardrails and refusal mechanisms have been removed, users are solely responsible for the outputs generated and for ensuring safe, legal deployment in downstream applications.

Downloads last month: -

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for OpenIntelligenceNet/LFM3-1.7B-Uncensored

Base model

LiquidAI/LFM3-1.7B-Base

Finetuned

LiquidAI/LFM3-1.7B

Finetuned

(8)

this model