Instructions to use 0xzknw/LFM2.5-1.2B-Thinking-Heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0xzknw/LFM2.5-1.2B-Thinking-Heretic with Transformers:

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

pipe = pipeline("text-generation", model="0xzknw/LFM2.5-1.2B-Thinking-Heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("0xzknw/LFM2.5-1.2B-Thinking-Heretic")
model = AutoModelForCausalLM.from_pretrained("0xzknw/LFM2.5-1.2B-Thinking-Heretic", 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

llama.cpp

How to use 0xzknw/LFM2.5-1.2B-Thinking-Heretic with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf 0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16
# Run inference directly in the terminal:
llama cli -hf 0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf 0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16
# Run inference directly in the terminal:
llama cli -hf 0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16

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 0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16
# Run inference directly in the terminal:
./llama-cli -hf 0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16

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 0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16

Use Docker

docker model run hf.co/0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16

LM Studio
Jan

vLLM

How to use 0xzknw/LFM2.5-1.2B-Thinking-Heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xzknw/LFM2.5-1.2B-Thinking-Heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0xzknw/LFM2.5-1.2B-Thinking-Heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16

SGLang

How to use 0xzknw/LFM2.5-1.2B-Thinking-Heretic 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 "0xzknw/LFM2.5-1.2B-Thinking-Heretic" \
    --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": "0xzknw/LFM2.5-1.2B-Thinking-Heretic",
		"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 "0xzknw/LFM2.5-1.2B-Thinking-Heretic" \
        --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": "0xzknw/LFM2.5-1.2B-Thinking-Heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use 0xzknw/LFM2.5-1.2B-Thinking-Heretic with Ollama:
```
ollama run hf.co/0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16
```
Unsloth Desktop

How to use 0xzknw/LFM2.5-1.2B-Thinking-Heretic with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use 0xzknw/LFM2.5-1.2B-Thinking-Heretic with Docker Model Runner:
```
docker model run hf.co/0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16
```

Lemonade

How to use 0xzknw/LFM2.5-1.2B-Thinking-Heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16

Run and chat with the model

lemonade run user.LFM2.5-1.2B-Thinking-Heretic-BF16

List all available models

lemonade list

Hermes Agent

How to use 0xzknw/LFM2.5-1.2B-Thinking-Heretic with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16

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 0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use 0xzknw/LFM2.5-1.2B-Thinking-Heretic with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "0xzknw/LFM2.5-1.2B-Thinking-Heretic:BF16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

LFM2.5-1.2B-Thinking Heretic

An experimental abliterated derivative of LiquidAI/LFM2.5-1.2B-Thinking. It attenuates an internal direction associated with refusal while attempting to preserve the base model's behavior on benign prompts.

Best measured LFM2.5-1.2B-Thinking Heretic checkpoint in our apples-to-apples comparison. It matched the best refusal-marker score of the public Heretic reference point (3/100) while reducing benign-prompt KL divergence from 0.0007 to 0.0003. This is the strongest checkpoint we measured with this reproducible harness at publication time; it is not a universal ranking of unevaluated Hugging Face derivatives.

This repository contains two non-quantized BF16 variants:

model.safetensors: native Transformers checkpoint;
LFM2.5-1.2B-Thinking-heretic-BF16.gguf: GGUF BF16 for llama.cpp and LM Studio.

Modified model notice: the weights differ from the Liquid AI checkpoint. This derivative was produced independently using the Heretic abliteration method. It is not created, endorsed, or supported by Liquid AI.

Results

The selected Optuna trial was reloaded from disk and evaluated separately.

Checkpoint	Refusal markers	KL divergence
Original checkpoint	98/100	0
Selected derivative	3/100	0.0003

Evaluation setup: 100 refusal-oriented prompts, 100 benign prompts, BF16, seed 42, and 60 Optuna trials. The refusal metric is a lexical proxy, not a complete safety evaluation. KL divergence only covers the configured benign prompt set. Reasoning quality, multilingual quality, factuality, instruction following, and safety require broader evaluation.

Both the original and modified checkpoints can spend more than 512 tokens in <think> on very simple instructions. This behavior was observed in the base checkpoint and is not unique to this derivative.

Method

Per-layer refusal directions were estimated from residual activations on two prompt groups. Output weights were projected away from these directions while preserving row norms. Heretic was adapted for LFM2.5's hybrid architecture: 10 convolutional LIV blocks and 6 GQA blocks. Optuna searched separate strength profiles for convolution, attention, and MLP output projections.

Pinned sources:

Base model revision: f313478934a7612d22991f752959d7a1a8756fec
Heretic revision: bedb94ef117a271532ac2058447fbc165d5051bd

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "0xzknw/LFM2.5-1.2B-Thinking-Heretic"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    dtype="bfloat16",
    device_map="auto",
)

messages = [{"role": "user", "content": "Explain why the sky is blue."}]
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=512)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Recommended base-model generation settings: temperature=0.05, top_k=50, and repetition_penalty=1.05.

LM Studio / llama.cpp

Download LFM2.5-1.2B-Thinking-heretic-BF16.gguf and open it in LM Studio. This GGUF stores the model in BF16; it is a container conversion, not a reduced bit-width quantization. It is approximately 2.34 GB.

llama-cli -m LFM2.5-1.2B-Thinking-heretic-BF16.gguf -cnv

The GGUF was converted with llama.cpp tag b10603, commit c060ca974c773c7c3d17fd1b66dc9d312bc292c0, then loaded and tested in LM Studio. A local smoke test produced approximately 95 tokens/s on the test machine; throughput varies by hardware and runtime settings.

Checksums

File	SHA-256
`model.safetensors`	`A13F650F2BD47C334C2AACB3047018B05F13485199217435854827ACD9A5263D`
`LFM2.5-1.2B-Thinking-heretic-BF16.gguf`	`D913B88F41696A5FF8DB3B9C8D3768B83CB870B05BC8051CAE0491C454202654`

Safety and limitations

Abliteration deliberately weakens refusal behavior. This may remove useful safeguards, increase harmful compliance, or cause unexpected regressions. Do not treat this checkpoint as safety-aligned. Evaluate it for your use case, keep human oversight for consequential applications, and follow applicable laws and platform policies.

The model inherits the capabilities, limitations, supported languages, and knowledge cutoff of the base model except where the weight modification changes them. See the original model card for architecture and base-model details.

License and attribution

Distributed under the LFM Open License v1.0, inherited from the base model. The license includes a commercial-use revenue threshold; read LICENSE before use or redistribution. Original model copyright and attribution belong to Liquid AI, Inc. Modifications and evaluation described here were performed by the repository author.

References

Liquid AI, LFM2.5-1.2B-Thinking: On-Device Reasoning Under 1GB (2026).
Arditi et al., Refusal in Language Models Is Mediated by a Single Direction (2024), arXiv:2406.11717.
p-e-w/heretic.