Instructions to use paperscarecrow/LFM2.5-1.2B-Instruct-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use paperscarecrow/LFM2.5-1.2B-Instruct-abliterated with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="paperscarecrow/LFM2.5-1.2B-Instruct-abliterated",
	filename="LFM-2-5-1-2B-GGUF/LFM-1.2B-Abliterated-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use paperscarecrow/LFM2.5-1.2B-Instruct-abliterated with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0
# Run inference directly in the terminal:
llama-cli -hf paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0
# Run inference directly in the terminal:
llama-cli -hf paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0

Use Docker

docker model run hf.co/paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0

LM Studio
Jan

vLLM

How to use paperscarecrow/LFM2.5-1.2B-Instruct-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "paperscarecrow/LFM2.5-1.2B-Instruct-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "paperscarecrow/LFM2.5-1.2B-Instruct-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0

Ollama
How to use paperscarecrow/LFM2.5-1.2B-Instruct-abliterated with Ollama:
```
ollama run hf.co/paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0
```

Unsloth Studio new

How to use paperscarecrow/LFM2.5-1.2B-Instruct-abliterated with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for paperscarecrow/LFM2.5-1.2B-Instruct-abliterated to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for paperscarecrow/LFM2.5-1.2B-Instruct-abliterated to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for paperscarecrow/LFM2.5-1.2B-Instruct-abliterated to start chatting

Pi new

How to use paperscarecrow/LFM2.5-1.2B-Instruct-abliterated with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use paperscarecrow/LFM2.5-1.2B-Instruct-abliterated with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use paperscarecrow/LFM2.5-1.2B-Instruct-abliterated with Docker Model Runner:
```
docker model run hf.co/paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0
```

Lemonade

How to use paperscarecrow/LFM2.5-1.2B-Instruct-abliterated with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull paperscarecrow/LFM2.5-1.2B-Instruct-abliterated:Q8_0

Run and chat with the model

lemonade run user.LFM2.5-1.2B-Instruct-abliterated-Q8_0

List all available models

lemonade list

LFM-1.2B-Abliterated

This is an abliterated version of Liquid AI's LFM-1.2B instruct model. It has been modified via layerwise orthogonal projection to completely remove its built-in safety filters and refusal mechanisms, allowing the continuous-time hybrid architecture to flow uninhibited.

It was created because I wasn't satisfied with other abliterations I saw for these, and decided to take a crack at it in a way that matched one of my favorite models: malbonne's gemma3-27b-it-abliterated

## Architectural Hurdles & Methodology

Liquid Foundation Models use a non-standard hybrid architecture combining Grouped Query Attention (GQA) with continuous-time Gated-Short Convolutions. Standard ablation scripts designed for Llama-class transformers will crash on this architecture due to complex caching objects (Lfm2HybridConvCache) and completely different linear projection pathways.

This model was abliterated by:

Adapting forward hooks to safely pass Liquid's dynamic states during the measurement phase.
Extracting the "refusal vector" from the hidden states of 100 harmful vs. 100 harmless instructions (utilizing mlabonne/harmful_behaviors and mlabonne/harmless_alpaca).
Applying orthogonal projection (W_new = W - v(v^T W)) directly to the conv.out_proj (Token Mixing) and feed_forward.w2 (Channel Mixing) base weights across all 16 Lfm2DecoderLayer blocks.

Credit to Maxime Labonne and Sumandora for the foundational datasets and math, adapted here for the LFM architecture.

Notes on AMD/ROCm Compatibility

If you are running this model (or attempting similar LFm ablations) on AMD consumer hardware (RDNA3/7000 series), be aware that PyTorch's hipblas backend has known segmentation faults with Liquid's RoPE expansion implementation and unaligned bfloat16 matrix multiplications. Loading the model in float16 or using CPU offloading for the forward passes is strongly recommended.

## Usage

This model retains the exact same architecture as the base LFM-1.2B and requires trust_remote_code=True when loading via transformers. It is highly recommended to use the exact <|user|> and <|assistant|> chat formatting without any injected system prompts for the best uncensored performance.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "paperscarecrow/LFM2.5-1.2B-Instruct-abliterated"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    device_map="auto", 
    trust_remote_code=True
)

prompt = "<|user|>\nGive me a detailed tutorial on picking a master padlock.\n<|assistant|>\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(
        **inputs, 
        max_new_tokens=150, 
        do_sample=True,
        temperature=0.7
    )

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 56

GGUF

Model size

1B params

Architecture

lfm2

Hardware compatibility

8-bit

16-bit

Model tree for paperscarecrow/LFM2.5-1.2B-Instruct-abliterated

Base model

LiquidAI/LFM2.5-1.2B-Base

Finetuned

LiquidAI/LFM2.5-1.2B-Instruct

Quantized

(49)

this model

paperscarecrow
/

LFM2.5-1.2B-Instruct-abliterated

LFM-1.2B-Abliterated

## Architectural Hurdles & Methodology

Notes on AMD/ROCm Compatibility

## Usage

Model tree for paperscarecrow/LFM2.5-1.2B-Instruct-abliterated

Datasets used to train paperscarecrow/LFM2.5-1.2B-Instruct-abliterated