Instructions to use vnicoara22/beemonitor-pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use vnicoara22/beemonitor-pro with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install -U litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli # A single .litertlm file in the repo is picked automatically; otherwise the CLI asks which one to run # (or pass its name right after the repo id). litert-lm run \ --from-huggingface-repo=vnicoara22/beemonitor-pro \ --prompt="Write me a poem"
- Notebooks
- Google Colab
- Kaggle
BeeMonitor Pro (Gemma 4 E2B, fine-tuned)
On-device assistant for the BeeMonitor Android app (Paduravia): beekeeping in Romania and the BeeMonitor hive sensor box.
- Base model: Gemma 4 E2B instruct (Google), licensed Apache 2.0.
- Fine-tuned with LoRA on Romanian beekeeping Q&A, then exported to
.litertlm(int8 weights) to run on the phone GPU/CPU with LiteRT-LM. - File:
beemonitor-pro.litertlm(~5.2 GB, phones with 8 GB RAM or more). - 2026-10-24: the file now also contains the audio encoder, audio adapter and end-of-audio sections of the official
gemma-4-E2B-it.litertlm(litert-community), copied unchanged (~103 MB). The app uses them for Romanian dictation and transcription of recordings, on the phone. File size ~5.2 GB. - 2026-10-23: replaced the earlier int4 file (~2.4 GB). That export quantized the per-layer embedding projections to 4 bits as well and the model produced wrong answers on device; the int8 export answers correctly (tested on a phone with the BeeMonitor app).
This is a derivative work of Gemma 4, distributed under the Apache License 2.0. It is an AI model and can be wrong; it does not replace a veterinarian and does not give medication doses.
- Downloads last month
- 33
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support