Upload folder using huggingface_hub

README.md

@@ -0,0 +1,32 @@
+---
+license: mit
+tags: [from-scratch, opcode, ternary, trit, execution-verified, tiny]
+---
+
+# Binary-Trit Coder (Clay's opcode model)
+
+A **from-scratch, 3.17M-param causal transformer** trained from *random init* on Issac's own opcode
+substrate — a bijective ternary ("trit") op grammar: `join (+)`, `take (−)`, `weave (×)` over digit leaves,
+prefix-notation, depth-2. No pretraining, no outside corpus.
+
+## Honest benchmark — its OWN domain, not Python
+The metric is **execution-verify rate**: sample a program, *run it for real*, check the model's answer.
+| Test | Score |
+|---|---|
+| in-distribution (depth-2, fresh) | **98.6%** |
+| OOD generalization (depth-3, never trained) | 47.0% |
+
+**This is NOT a Python code-gen model.** It has an 18-token opcode vocab; it will score ~0 on
+LiveCodeBench/SciCode (wrong domain). Its "learn from doing" signal is the verify-rate above.
+
+## The chrysalis (capability layers, all execution-verified)
+- variables/let-bindings (69.5% end-to-end; 100% with a calculator + show-work)
+- ping-pong φ-lattice solver — recovers a hidden intermediate 100%
+- calc-offload, dark-space inference, combustion candidate-spark
+
+## Files
+`scratch_coder.pt` (weights + vocab), `config.json`. Architecture + inference in
+[github.com/issdandavis/loom](https://github.com/issdandavis/loom) `scratch_coder.py`.
+
+*Thesis: coding is finite + bijective + execution-verifiable, so a small model from random init can MASTER
+the mapping — proven here at 98.6%.*

config.json

@@ -0,0 +1,9 @@
+{
+  "model_type": "trit-opcode-gpt",
+  "architecture": "TinyGPT (from-scratch causal transformer)",
+  "d_model": 256, "heads": 8, "layers": 4, "max_len": 24,
+  "vocab": ["<pad>","<bos>","<eos>","=","-","0","1","2","3","4","5","6","7","8","9","join","take","weave"],
+  "ops": {"join": "+", "take": "-", "weave": "*"},
+  "trained_from": "random init (no pretraining)",
+  "metric": "execution-verify rate (run the emitted program, check the answer)"
+}

scratch_coder.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0cf4a29a6a159241ed812ed5ecaac80ec30978d8ee708d03aa93bffcf15dae
+size 12722131