Upload README.md with huggingface_hub

README.md

@@ -29,7 +29,7 @@ It is the model invoked by `paw.compile(spec, compiler="paw-4b-gpt2")`.
 
 1. The 4B compiler generates a short "pseudo-program" (a task description plus a few I/O examples) from the spec.
 2. The text `chat_template(spec) + pseudo-program + 64 prefix tokens` is run through the compiler; the mapper reads the 64 prefix hidden states and emits per-layer LoRA `A`/`B` matrices as a learned mixture of basis matrices.
-3. The resulting LoRA (~5 MB) is the **program**. It loads onto the GPT-2 interpreter and runs locally/offline (including in-browser).
+3. The resulting LoRA (about 5 MB) is the **program**. It loads onto the GPT-2 interpreter and runs locally/offline (including in-browser).
 
 ## Status