SmolLM2-135M-Instruct-ET

ExecuTorch .pte model converted from HuggingFaceTB/SmolLM2-135M-Instruct for on-device inference with ToMogo.

Model Details

Property	Value
Source	HuggingFaceTB/SmolLM2-135M-Instruct
Format	executorch
Quantization	int4 weight-only
Backend	xnnpack
Fusion	disabled
Total Size	241.4 MB

Files

File	Size
README.md	0.0 MB
chat_template.jinja	0.0 MB
export_config.json	0.0 MB
model.pte	238.0 MB
tokenizer.json	3.4 MB
tokenizer_config.json	0.0 MB

Usage

Download all files into a single directory and load with ExecuTorch on Android:

val engine = ExecuTorchEngine(modelDir = "/path/to/SmolLM2-135M-Instruct-ET")
engine.prefill(prompt) { token -> print(token) }

---

Auto-generated by ToMogo upload pipeline.