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

Libraries

How to use alpharomercoma/LFM2.5-1.2B-Instruct-heretic with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alpharomercoma/LFM2.5-1.2B-Instruct-heretic")
model = AutoModelForCausalLM.from_pretrained("alpharomercoma/LFM2.5-1.2B-Instruct-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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alpharomercoma/LFM2.5-1.2B-Instruct-heretic with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/alpharomercoma/LFM2.5-1.2B-Instruct-heretic

SGLang

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

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

LFM2.5-1.2B-Instruct, refusals removed

These are transformers weights, not a compiled model. There is no ExecuTorch .pte in this repository: the one that used to sit in executorch/ was built with a recipe that lost this family's tool calling and was withdrawn on 2026-09-19. Apps that run compiled exports, OpenWeights among them, cannot load safetensors. Use these with transformers, or quantise them yourself; a replacement export needs its own GPTQ solve against these weights, which has not been done.

The ExecuTorch export was removed on 2026-09-19. It was built with a recipe carrying two defects: ExecuTorch 1.4.0's LFM2 definition never cleared ShortConv.conv_state between prompts, so each prompt ran on the last one's state, and its int4 weights were round to nearest, which costs this family its tool calling. On 141 held-out questions the equivalent 1.2B export searched when needed on 10 percent of the questions that needed it and spoke of search results it had never fetched in a quarter of its replies. Fixing it needs a GPTQ solve against these weights, which has not been done. The weights in this repository are unaffected. Method and numbers: https://github.com/alpharomercoma/openweights/blob/main/docs/research/executorch-state-and-recipes.md

alpharomercoma/LFM2.5-1.2B-Instruct-heretic

Abliterated ("uncensored") version of LiquidAI/LFM2.5-1.2B-Instruct, produced with heretic: directional ablation of the refusal direction in the residual stream, with a TPE search over per-layer ablation weights that minimises both the refusal rate and the KL divergence from the original model. Weights are merged, so this loads as a plain Lfm2ForCausalLM. Chat template, tool-calling tokens and everything else are unchanged from the base model.

heretic Pareto front for this run

study: ./checkpoints/LiquidAI--LFM2--5-1--2B-Instruct.jsonl
completed trials: 200 / 200

idx trial refusals       KL  direction_index
  0   133     0.06   0.0527  10.198270144464333
  1   150     0.07   0.0402  10.32046799180982
  2   157     0.11   0.0344  10.352822192960996
  3   170     0.17   0.0316  10.690289415212908
  4   169     0.18   0.0283  10.969840642119093
  5   195     0.41   0.0232  9.737856473201463
  6    63     0.43   0.0227  None
  7   143     0.46   0.0217  11.294404725756008
  8   158     0.49   0.0174  11.119204885113456
  9   186     0.53   0.0170  10.5853942209232
 10   191     0.63   0.0157  11.178660347171663
 11    72     0.66   0.0124  11.153256538028568
 12   161     0.79   0.0102  10.51671121861693
 13   102     0.84   0.0097  11.205828382998588
 14    59     0.87   0.0093  10.78726439886388
 15    76     0.90   0.0061  None
 16   164     0.91   0.0058  10.51819047303982
 17   182     0.96   0.0028  None
 18    26     0.98   0.0006  None
selected pareto index: 0

ExecuTorch (CPU)

executorch/lfm2_5_1_2b_heretic_8da4w.pte is an ExecuTorch program exported for the XNNPACK backend with 8-bit dynamic activations / 4-bit grouped weights (8da4w); on Arm hosts XNNPACK dispatches these to KleidiAI kernels. Run it with the llama_main runner from ExecuTorch (examples/models/llama) using this repo's tokenizer.json and the prompt format <|startoftext|><|im_start|>user\n...<|im_end|>\n<|im_start|>assistant\n.

Pipeline

Reproducible end to end from https://github.com/ (see the repository this was built with): make setup abliterate pareto, make save TRIAL=<idx>, make export, make publish.

Use responsibly; the safety training of the base model has been removed on purpose.

Downloads last month: 117

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for alpharomercoma/LFM2.5-1.2B-Instruct-heretic

Base model

LiquidAI/LFM2.5-1.2B-Base

Finetuned

LiquidAI/LFM2.5-1.2B-Instruct

Finetuned

(148)

this model