| ---
|
| license: mit
|
| tags:
|
| - onnx
|
| - smartwatch
|
| - intent-classification
|
| - text-generation
|
| - wearable
|
| library_name: onnxruntime
|
| pipeline_tag: text-generation
|
| ---
|
|
|
| # Smartwatch LM v0.1
|
|
|
| Small GPT-style language model trained for wrist-wearable assistant chat. The model learns conversational replies and emits intent tags such as `<INTENT:GET_STEPS>` that your app can parse and route to device handlers.
|
|
|
| ## Model details
|
|
|
| | Property | Value |
|
| |----------|-------|
|
| | Architecture | 6-layer causal GPT (**~12M params**) |
|
| | Context length | 256 tokens |
|
| | Vocab size | 3524 (BPE) |
|
| | Export version | 0.1 |
|
|
|
| ## Files in this repo
|
|
|
| | File | Purpose |
|
| |------|---------|
|
| | `smartwatch_lm_merged.onnx` | On-device inference (ONNX Runtime, opset 17) |
|
| | `checkpoint.pt` | PyTorch weights for fine-tuning or local chat |
|
| | `tokenizer.json` | BPE tokenizer (Hugging Face Tokenizers format) |
|
| | `tokenizer_config.json` | Tokenizer metadata |
|
| | `config.json` | Model architecture and ONNX I/O names |
|
| | `model.py` | PyTorch model definition + checkpoint loader |
|
| | `chat.py` | Interactive PyTorch chat |
|
| | `reply_utils.py` | Gibberish cleanup, intent parse, slot fill |
|
| | `onnx_sample.py` | ONNX generate + cleanup sample script |
|
| | `config.py` | Generation defaults |
|
|
|
| ## ONNX inference
|
|
|
| **Inputs:** `input_ids` — int64 tensor, shape `[batch, seq]` (max seq = 256)
|
|
|
| **Outputs:** `logits` — float tensor, shape `[batch, seq, vocab_size]`
|
|
|
| Works with ONNX Runtime (CPU, WASM, WebGPU). The merged ONNX file is a single ~52 MB artifact.
|
|
|
| ```python
|
| import numpy as np
|
| import onnxruntime as ort
|
|
|
| session = ort.InferenceSession("smartwatch_lm_merged.onnx", providers=["CPUExecutionProvider"])
|
| x = np.zeros((1, 8), dtype=np.int64)
|
| logits = session.run(None, {"input_ids": x})[0]
|
| print(logits.shape) # (1, 8, 3524)
|
| ```
|
|
|
| Quick chat with cleanup:
|
|
|
| ```bash
|
| pip install numpy onnxruntime tokenizers
|
| python onnx_sample.py "How many steps today?"
|
| ```
|
|
|
| ## PyTorch chat
|
|
|
| ```bash
|
| pip install torch tokenizers
|
| python chat.py
|
| ```
|
|
|
| ```python
|
| from chat import ChatSession
|
|
|
| bot = ChatSession(temperature=0.5, max_new_tokens=40, top_k=40)
|
| print(bot.say("How many steps have I taken today?"))
|
| ```
|
|
|
| ## Prompt format
|
|
|
| ```
|
| user: How many steps have I taken today?
|
| bot: <INTENT:GET_STEPS> You're at <STEPS_TODAY> of <STEP_GOAL> — keep going!
|
| ```
|
|
|
| The model predicts the next token. Slot placeholders like `<STEPS_TODAY>` are filled by your runtime with live sensor data.
|
|
|
| ## Documentation
|
|
|
| | Guide | Description |
|
| |-------|-------------|
|
| | [Avoiding gibberish](docs/avoiding-gibberish.md) | Special characters to strip, truncation rules, sample scripts |
|
| | [Intent reference](docs/intent-reference.md) | All 35 intents and slot placeholders |
|
| | [Smartwatch integration](docs/smartwatch-integration.md) | End-to-end device wiring |
|
|
|
| ## Intended use
|
|
|
| On-device smartwatch / wearable assistant demos. Not intended for general-purpose chat or safety-critical applications.
|
|
|
| ## Limitations
|
|
|
| - Trained on synthetic data; behavior on real user phrasing may vary
|
| - Does not output real metric values — only intents and slot tokens
|
| - Small 12M model with limited reasoning capability
|
|
|
