|
Download README.md from Unt1l1f1nd/esp32-tiny-coding-model: direct link, hf CLI and curl.
- Browser
- Download file 2.47 kB
-
https://huggingface.co/Unt1l1f1nd/esp32-tiny-coding-model/resolve/main/README.md
- Command line
-
hf download hf://Unt1l1f1nd/esp32-tiny-coding-model/README.md
-
curl -L -o README.md https://huggingface.co/Unt1l1f1nd/esp32-tiny-coding-model/resolve/main/README.md
2.47 kB
| license: mit | |
| library_name: custom | |
| tags: | |
| - esp32 | |
| - tinyml | |
| - microcontroller | |
| - code-generation | |
| # esp32-tiny-coding-model | |
| A 3M-parameter model that runs inside an ESP32-S3. You type a sentence in English, it writes a small program for | |
| the board's 128x64 screen, and the same chip runs it. No internet, no server. | |
|  | |
| | | | | |
| |---|---| | |
| | Model | 2.9M core + 0.8M lookup table (Per-Layer Embeddings), 2.1 MB at 4-bit | | |
| | Speed | about 9 tokens/s on the chip, "draw a house" in 5.6 s | | |
| | Held-out requests | 98% draw the same picture as the reference | | |
| It writes in a small Python-like language (`clear`, `text`, `pixel`, `line`, `rect`, `fill`, `circle`, `wait`, | |
| variables, `for`, `while`, `if`), and an interpreter on the chip runs it with limits on steps and waiting, so | |
| whatever the model writes, the chip stays in charge. It understands requests in the style it was trained on; a | |
| sentence far from them can draw the wrong thing. | |
| Code, training data generator, interpreter and firmware: [github.com/moudrkat/esp32-ai](https://github.com/moudrkat/esp32-ai), | |
| a fork of [slvDev/esp32-ai](https://github.com/slvDev/esp32-ai), whose runtime and firmware this runs on. | |
| ## Files | |
| | file | what | | |
| |---|---| | |
| | `esp32-oled-full.bin` | everything for the board in one image: bootloader, firmware and model | | |
| | `model.bin` | the model alone, as the firmware reads it from flash (offset `0x110000`) | | |
| | `tokenizer.json` | its tokenizer (byte-level BPE, 1,079 tokens) | | |
| ## Run it | |
| Hardware: an ESP32-S3 board with 16 MB flash and 8 MB PSRAM (octal), and a 128x64 SSD1306 I2C OLED on | |
| **SDA = GPIO 18, SCL = GPIO 8**. | |
| ```bash | |
| pip install esptool | |
| esptool --chip esp32s3 --port /dev/ttyACM0 write-flash 0x0 esp32-oled-full.bin | |
| ``` | |
| Then open the serial port at 115200 baud, type a request and press Enter, for example `draw a house`, | |
| `countdown from 5 then happy birthday`, `bounce a ball twice quickly`. The repo has a small terminal for it: | |
| `scripts/oled_talk.py`. | |
| Other wiring or another screen: build the firmware from the repo (`scripts/deploy.sh oled`), which also checks the | |
| C runtime against the PyTorch model before it flashes. | |
| ## Training data | |
| About 300,000 request -> program pairs generated by rules (no model involved), each program run by the reference | |
| interpreter before it is kept. Reproducible with `research/oled/gen.py` in the repo. | |
| MIT © Kateřina Fajmanová | |