| --- |
| title: FSI_ECHO |
| emoji: 🧬 |
| colorFrom: purple |
| colorTo: indigo |
| sdk: gradio |
| sdk_version: "5.0.0" |
| app_file: app.py |
| pinned: false |
| license: apache-2.0 |
| --- |
| |
| # 🧬 FSI_ECHO — Morphing Code Swarm |
| |
| **World's smallest production code AI: 2.6M params, 1.3MB at Q4, runs on any phone.** |
| |
| ## Architecture — Novel "Morphing Code Swarm" |
| |
| | Component | What it does | |
| |-----------|-------------| |
| | **Morph Embedding** | Tokens transform based on context (causal sliding window) | |
| | **Nanobot Swarm** | 512 nanobots with scout/combat dual-mode routing | |
| | **Assembly Blocks** | Multi-head attention with adaptive gating | |
| | **Self-Verification** | Built-in confidence scoring per token | |
| | **Closed-Loop Debug** | Generates, verifies syntax, and iteratively refines | |
| |
| ## Metrics |
| |
| - Parameters: 2,621,578 |
| - FP32 size: 10.5 MB |
| - Q4 size: 1.31 MB — fits on any phone |
| - Training loss: 8.4 → 0.0 (trained on 2400+ code examples) |
| - Speed: ~10 tok/s on CPU |
| - Context: 2048 tokens |
| |
| ## Usage |
| |
| ```python |
| from fsi_echo import FSIEchoModel, CodeTokenizer, ClosedLoopDebugger |
| import torch |
|
|
| model = FSIEchoModel() |
| tok = CodeTokenizer() |
| ckpt = torch.load('prod2_final.pt', map_location='cpu', weights_only=True) |
| model.load_state_dict(ckpt['model']) |
| model.eval() |
| |
| # Generate code |
| result = model.generate(tok, 'def reverse_str', max_tokens=50) |
| print(result['generated']) |
| |
| # Debug code |
| debugger = ClosedLoopDebugger(model, tok) |
| result = debugger.debug("def add(a, b):\n a + b") |
| print(result['code']) |
| ``` |
| |
| ## License |
| Apache 2.0 |
| |
