Upload README.md with huggingface_hub

README.md

@@ -11,16 +11,27 @@ tags:
   - int4
 ---
 
+![MobileTransformers](mobiletransformers_banner.png)
+
 # google/functiongemma-270m-it — MobileTransformers package
 
 On-device (Android) package exported from **google/functiongemma-270m-it** with MobileTransformers.
 
+## What this package can do
+- `core` — shared files every other group needs
+- `inference` — generate or score on device
+- `train` — **fine-tune on device**, then merge the adapter back into the base weights
+
+## Fine-tuning method
+- **lora** — LoRA — low-rank adapters on the attention projections.
+- Rank: `8`
+- Adapted modules: `q_proj`, `v_proj`
+
 ## Provenance
 - Base model: `google/functiongemma-270m-it`
 - Selected task: `text-generation-with-past`
-- PEFT methods: lora
 - Quantization: int4
-- Toolchain: optimum-onnx 0.1.0, transformers 4.57.6, ort-training 1.23.0+cpu, ort-genai None
+- Toolchain: optimum-onnx 0.1.0, transformers 4.57.6, ort-training 1.23.0+cpu
 
 ## Licenses
 - Framework: not declared in this package — see the repository
@@ -28,13 +39,44 @@ On-device (Android) package exported from **google/functiongemma-270m-it** with
 
 ## Android runtime
 - Minimum API: 28
-- Recommended device memory (MB): None
 - Required ABIs: any
 
 ## Variants
 
 | id | EP | quant | engines | features | min API | rec. RAM (MB) |
 | --- | --- | --- | --- | --- | --- | --- |
-| cpu-int4 | cpu | int4 | native | core, inference, train | 28 | None |
+| cpu-int4 | cpu | int4 | native | core, inference, train | 28 | — |
 
 Default variant: `cpu-int4`.
+
+## Running this model
+
+This is a **MobileTransformers package**, not a plain Hugging Face model: it is a manifest plus per-variant ONNX stages and a weight-handoff map. `transformers`, `optimum` and plain `onnxruntime` cannot load it. Use the framework:
+
+**https://github.com/martinkorelic/mobiletransformers**
+
+```kotlin
+// Android — pulls, verifies and installs on first use.
+val model = MobileTransformers.fromPretrained(
+    context = context,
+    repoId  = "mobiletransformers/functiongemma-270m-it",
+)
+```
+
+```bash
+# Host — download and inspect the package without a device.
+mobiletransformers pull --repo-id mobiletransformers/functiongemma-270m-it
+```
+
+## Citation
+
+If you are using this framework for your own work, please cite:
+
+```bibtex
+@misc{mobiletransformers2025,
+  author       = {Koreli\v{c}, Martin and Pejovi{\'c}, Veljko},
+  title        = {MobileTransformers: An On-Device LLM PEFT Framework for Fine-Tuning and Inference},
+  year         = {2025},
+  howpublished = {\url{https://gitlab.fri.uni-lj.si/lrk/mobiletransformers}}
+}
+```