base on A "large" language model running on a microcontroller # llama4micro 🦙🔬 A "large" language model running on a microcontroller.  ## Background I was wondering if it's possible to fit a non-trivial language model on a microcontroller. Turns out the answer is some version of yes! (Later, things got a bit out of hand and now the prompt is based on objects detected by the camera.) This project is using the [Coral Dev Board Micro](https://coral.ai/products/dev-board-micro) with its [FreeRTOS toolchain](https://coral.ai/docs/dev-board-micro/freertos/). The board has a number of neat [hardware features](https://coral.ai/docs/dev-board-micro/get-started/#the-hardware), but – most importantly for our purposes – it has 64MB of RAM. That's tiny for LLMs, which are typically measured in the GBs, but comparatively huge for a microcontroller. The LLM implementation itself is an adaptation of [llama2.c](https://github.com/karpathy/llama2.c) and the [tinyllamas](https://huggingface.co/karpathy/tinyllamas/tree/main) checkpoints trained on the [TinyStories](https://huggingface.co/datasets/roneneldan/TinyStories) dataset. The quality of the smaller model versions isn't ideal, but good enough to generate somewhat coherent (and occasionally weird) stories. > [!NOTE] > Language model inference runs on the 800 MHz [Arm Cortex-M7](https://developer.arm.com/Processors/Cortex-M7) CPU core. Camera image classification uses the [Edge TPU](https://coral.ai/technology/) and a [compiled](https://coral.ai/docs/edgetpu/compiler/) [YOLOv5 model](https://github.com/ultralytics/yolov5). The board also has a second 400 MHz [Arm Cortex-M4](https://developer.arm.com/Processors/Cortex-M4) CPU core, which is currently unused. ## Setup Clone this repo with its submodules [`karpathy/llama2.c`](https://github.com/karpathy/llama2.c), [`google-coral/coralmicro`](https://github.com/google-coral/coralmicro), and [`ultralytics/yolov5`](https://github.com/ultralytics/yolov5). ```bash git clone --recurse-submodules https://github.com/maxbbraun/llama4micro.git cd llama4micro ``` The pre-trained models are in the [`models/`](models/) directory. Refer to the [instructions](models/README.md) on how to download and convert them. Build the image: ```bash mkdir build cd build cmake .. make -j ``` Flash the image: ```bash python3 -m venv venv . venv/bin/activate pip install -r ../coralmicro/scripts/requirements.txt python ../coralmicro/scripts/flashtool.py \ --build_dir . \ --elf_path llama4micro ``` ## Usage 1. The models load automatically when the board powers up. - This takes ~7 seconds. - The green light will turn on when ready. 2. Point the camera at an object and press the button. - The green light will turn off. - The camera will take a picture and detect an object. 3. The model now generates tokens starting with a prompt based on the object. - The results are streamed to the serial port. - This happens at a rate of ~2.5 tokens per second. 4. Generation stops after the end token or maximum steps. - The green light will turn on again. - Goto 2. ", Assign "at most 3 tags" to the expected json: {"id":"5053","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"