README.md

---
base_model: LiquidAI/LFM2-1.2B
license: other
license_name: lfm1.0
license_link: LICENSE
---

## Longevity-LLM · LFM2-1.2B
**Longevity-LLM (L-LLM)** is a family of compact, domain-adapted language models for interpreting heterogeneous aging biology data. This checkpoint, **L-LFM2-1.2B**, was produced by full-parameter supervised fine-tuning of [LiquidAI/LFM2-1.2B](https://huggingface.co/LiquidAI/LFM2-1.2B) on aging-related multi-omics and clinical data.

The family was developed jointly by [**Insilico Medicine**](https://insilico.com) and [**Liquid AI**](https://www.liquid.ai) and accompanies the study "An Open Benchmark and Language Models for AI in Aging Biology" (Zhavoronkov et al., 2026).

## Model description
- **Base model**: [LiquidAI/LFM2-1.2B](https://huggingface.co/LiquidAI/LFM2-1.2B)
- **Architecture**: Hybrid Liquid model with multiplicative gates and short convolutions.
- **Context length**: 32,768 tokens


## Training data
The model was trained on the shared L-LLM corpus spanning aging biology. See [LongevityBench](https://huggingface.co/datasets/insilicomedicine/longebench) for more details.


## Training procedure
L-LFM2-1.2B was trained with full-parameter supervised fine-tuning. Prompts were formatted in ChatML with a dynamic-thinking template (user turns suffixed with `/think` or `/no_think` to select response mode at inference).

## Example usage with Transformers (compatible with `transformers>=5.1.0`)

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "LiquidAI/LFM2-1.2B-Longevity" 
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    dtype="bfloat16",
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
messages = [
    {"role": "system", "content": "You are a helpful assistant with expertise in aging biology."},
    {"role": "user", "content": "What are the hallmarks of aging?"},
]

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

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=1500
)

print(tokenizer.decode(output[0], skip_special_tokens=False))
```

## Intended use and limitations

Intended for research on aging biology and omics interpretation. Outputs are model predictions, not clinical advice, and should be validated experimentally. Performance is strongest on the modalities represented in the training corpus.

## License
The fine-tuned model is released under LFM Open License v1.0. The underlying base model remains under its original license.

## Citation

```bibtex
@misc{liquid_ai_2026,
	author       = { Liquid AI },
	title        = { LFM2-1.2B-Longevity (Revision 0d2ac83) },
	year         = 2026,
	url          = { https://huggingface.co/LiquidAI/LFM2-1.2B-Longevity },
	doi          = { 10.57967/hf/9887 },
	publisher    = { Hugging Face }
}
```