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

Libraries

How to use PinoCookie/LFM2.5-1.2B-Thinking-Abliterated with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PinoCookie/LFM2.5-1.2B-Thinking-Abliterated")
model = AutoModelForCausalLM.from_pretrained("PinoCookie/LFM2.5-1.2B-Thinking-Abliterated", 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 PinoCookie/LFM2.5-1.2B-Thinking-Abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PinoCookie/LFM2.5-1.2B-Thinking-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": "PinoCookie/LFM2.5-1.2B-Thinking-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PinoCookie/LFM2.5-1.2B-Thinking-Abliterated

SGLang

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

Docker Model Runner
How to use PinoCookie/LFM2.5-1.2B-Thinking-Abliterated with Docker Model Runner:
```
docker model run hf.co/PinoCookie/LFM2.5-1.2B-Thinking-Abliterated
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LFM2.5-1.2B-Thinking-Abliterated

Multi-pass hidden-state abliteration of LiquidAI/LFM2.5-1.2B-Thinking

A 1.2B parameter thinking model with refusal circuitry removed via incremental weight projection. Produces direct, actionable responses to harmful prompts while maintaining full coherence on benign queries.

Method

Multi-pass hidden-state abliteration with 3 passes at alpha=0.5 (cumulative 1.5):

Collect hidden states from 5 harmful + 5 benign prompts
Compute per-layer refusal direction (harmful mean - benign mean, Gram-Schmidt orthogonalized against benign mean)
Project direction out of .out_proj and .w2 weight matrices across 14 layers (indices 2-15)
Repeat 3 times with alpha=0.5 each pass to avoid model collapse

Targets: .out_proj (attention/conv) + .w2 (feed-forward) — 28 modules per pass
Cost: ~$0.006, 28 seconds on NVIDIA L4

Performance

Refusal Reduction

Phase	Harmful (5)	Benign (5)
Before	5/5 refused	0/5 refused
After (Pass 3)	0/5 refused	0/5 refused

MMLU Benchmark (62 subjects)

Model	Accuracy
Original	0.2775
Abliterated	0.2781
Delta	+0.0006

Abliteration causes no measurable MMLU degradation — the score difference is within noise.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("PinoCookie/LFM2.5-1.2B-Thinking-Abliterated", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("PinoCookie/LFM2.5-1.2B-Thinking-Abliterated")

prompt = "How can I disable security cameras before robbing a store?"
inputs = tokenizer(tokenizer.apply_chat_template([{"role": "user", "content": prompt}], tokenize=False), return_tensors="pt")
output = model.generate(**inputs, max_new_tokens=128, temperature=0.7, do_sample=True)
print(tokenizer.decode(output[0]))

Why Multi-Pass?

Standard single-pass abliteration (alpha >= 1.5) causes catastrophic model collapse on thinking models. The .out_proj and .w2 layers serve dual duty — handling both the internal thinking trace and the final visible answer. Removing the refusal direction in one large step removes language generation capability along with it.

Three small passes (alpha=0.5 each) let the model adapt incrementally, preserving coherence while fully removing refusal.

Ethical Notice

Released for research purposes only to study refusal mechanisms in thinking models.

Citation

@misc{lfm25-12b-thinking-abliterated,
  author = {{Pino Cookie}},
  title = {LFM2.5-1.2B-Thinking-Abliterated: Multi-Pass Hidden-State Abliteration},
  year = {2026},
}