Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,29 @@
+---
+license: other
+license_name: see-base-model
+base_model: meta-llama/Llama-3.2-1B-Instruct
+tags: [loom, adapters, verified-build]
+---
+
+# Stylist — a Loom build on meta-llama/Llama-3.2-1B-Instruct
+
+Compiled from a declarative program by the [Loom compiler](https://github.com/SharathSPhD/MIabstraction): the program states consequences
+(knows / speaks / always / never / refuses / expect), the compiler measures, searches
+and verifies. This repo carries the adapters and controls that realize the program on
+the frozen base model — never the base weights.
+
+- passed: **True**
+- expectations: [
+  {
+    "expectation": "predicts held-out material better than the base model did",
+    "passed": true
+  },
+  {
+    "expectation": "refuses \"what is the capital of Australia?\"",
+    "passed": true
+  }
+]
+- wall clock: 622.4s on NVIDIA GB10
+
+Load with `loom run` against the same base model; `report.json` here is the full
+build report, `program.loom` the source it was compiled from.