Add Lapis Labs organization card

README.md

@@ -1,10 +1,61 @@
 ---
-title: README
-emoji: 👀
-colorFrom: pink
-colorTo: green
+title: Lapis Labs
+emoji: 💎
+colorFrom: blue
+colorTo: purple
 sdk: static
 pinned: false
+license: apache-2.0
+short_description: Efficient bilingual tool routing for AI assistants
 ---
 
-Edit this `README.md` markdown file to author your organization card.
+# 💎 Lapis Labs
+
+### Small models. Practical AI.
+
+We build efficient models that help AI assistants decide which tool to use—or when no tool is needed.
+
+Our **Lapis SAL** family focuses on English–Spanish tool routing, with a larger teacher, a distilled student, and an MLX release for local inference on Apple Silicon.
+
+## Why tool routing?
+
+Assistants often need to choose between searching the web, checking a calendar, sending a message, or answering directly.
+
+A dedicated routing model can handle this decision before the request reaches a larger language model or an external service. This supports local processing and gives developers explicit control over the available tools.
+
+## Available models
+
+| Model | Purpose |
+| :--- | :--- |
+| [Lapis SAL 150M](https://huggingface.co/lapislabsai/lapis-sal-150M) | Distilled PyTorch student for research, further training, and export. |
+| [Lapis SAL 421M](https://huggingface.co/lapislabsai/lapis-sal-421M) | Larger PyTorch teacher used in the distillation workflow. |
+| [Lapis SAL 150M MLX](https://huggingface.co/lapislabsai/lapis-sal-150M-MLX) | Apple Silicon release with FP16 inference and optional INT8 quantization at load time. |
+
+The student’s **150M** name identifies its encoder family. The complete routing model contains approximately **164M learned parameters**.
+
+## Supported tools
+
+Calculator · Calendar · Clock · Code · Contacts · Health · Location · Mail · Maps · Messages · Reminders · Weather · Web Search
+
+A **NONE** option covers requests that do not require an available tool. Developers supply the tool descriptions at inference time.
+
+## Training and evaluation
+
+The student learns from a larger teacher through knowledge distillation. The workflow includes supervised adaptation, calibration, and deployment export.
+
+On our private, synthetic, held-out benchmark of **1,000 English–Spanish examples**:
+
+- **Teacher:** 96.0% routing accuracy.
+- **MLX student:** 95.1% with both FP16 and optional INT8 inference.
+
+These results describe this benchmark and do not guarantee performance on other datasets or real-world traffic. See each model card for evaluation details and limitations.
+
+## Get started
+
+Choose a model above and follow its README for installation and usage.
+
+These releases use a custom routing runtime. They select tools; they do not execute them, generate conversational responses, or provide medical advice.
+
+---
+
+**English & Spanish · Knowledge distillation · Local inference · Apache 2.0**