Upload README.md with huggingface_hub

README.md

@@ -11,16 +11,11 @@ short_description: Small models, narrow tasks
 
 # Glassbox
 
-Small models, narrow tasks. Trained from scratch, under 100M parameters, each doing one thing.
+Small models, narrow tasks.
 
-The 91M Bulgarian model against INSAIT's BgGPT-Gemma-2-2.6B, 28× larger:
+Trained from scratch, under 100M parameters, each doing one thing. The cards carry the
+losses as well as the wins.
 
-| | ours | theirs |
-|---|---|---|
-| fluency judging, 2000 pairs | **0.9305** | 0.9175 |
-| bits per character, same text | 1.3041 | **1.1600** |
-
-One win, one loss, both on the [card](https://huggingface.co/glassbox/gpt-alpha-bg-91m).
-[bg-eval](https://github.com/iksnerd/bg-eval) re-runs them without trusting us.
-
-[restorer-interp-lab.iksnerd.workers.dev](https://restorer-interp-lab.iksnerd.workers.dev)
+[restorer-interp-lab.iksnerd.workers.dev](https://restorer-interp-lab.iksnerd.workers.dev) ·
+[bg-eval](https://github.com/iksnerd/bg-eval), the loader and eval harness — reproduce the
+numbers on the cards yourself