distil-lfm25-home-assistant

A fine-tuned version of LiquidAI/LFM2.5-350M for multi-turn smart home control via tool calling, trained using the distil labs platform.

This model converts natural language commands ("turn off the kitchen lights," "set the thermostat to 72") into structured function calls, handling multi-turn conversations where users adjust commands or issue sequences.

Results

Metric	Teacher (120B)	LFM2.5-350M Base	LFM2.5-350M Tuned
Tool Call Equivalence	92.11%	63.2%	96.7%
ROUGE	98.53%	94.6%	99.4%

The tuned model beats the 120B teacher by 4.6 percentage points on smart home control.

Training Details

Parameter	Value
Base model	LiquidAI/LFM2.5-350M
Teacher model	GPT-oss-120B
Task type	Multi-turn tool calling (closed-book)
Training data	distil-labs/distil-smart-home
Training method	SFT with LoRA
Platform	distil labs

Training Progress

Epoch	Tool Call Equivalence
0 (base)	63.2%
1	96.1%
2	96.1%
3	96.7%
4	96.7%

Usage

This model uses the LFM2.5 tool calling format with <|tool_call_start|> and <|tool_call_end|> tags:

<|tool_call_start|>[function_name(arg1="value1", arg2=42)]<|tool_call_end|>

Deployment

This model is a natural fit for embedded deployment on smart home hubs and IoT gateways using the ONNX runtime, where sub-second latency on a low-power NPU means voice commands execute without a round trip to the cloud. It also works with Ollama, vLLM, llama.cpp, or any inference runtime that supports Safetensors.

Blog Post

For the full writeup, see: Fine-Tuning Liquid's LFM2.5: Accurate Tool Calling at 350M Parameters

License

This model is licensed under the LFM Open Model License v1.0.