Add company details + tokenizer/model benchmarks to org card

README.md

@@ -1,17 +1,22 @@
----
-title: ASTERIZER
-emoji: 🚀
-colorFrom: gray
-colorTo: gray
-sdk: static
-pinned: false
----
-
-# ASTERIZER
-
-**Building AI — from the model to the device.**
-
-- **LUNA-100M** — pretrained on 4.5B tokens, then RAG + MCP instruction-tuned
-- **LUNA-300M** — pretrained on 4.5B tokens (scale-up from 100M)
-- **LUNA-1B** — in progress
-- **Tokenizer** — multilingual BPE (128K / 64K / 8K)
+---
+title: ASTERIZER
+emoji: 🚀
+colorFrom: gray
+colorTo: gray
+sdk: static
+pinned: false
+---
+
+# ASTERIZER
+
+**Building AI from the model to the device** — self-hosted language models, a memory layer, application framework, and on-device AI, engineered in-house with 100% owned IP.
+
+**Models (trained from scratch)**
+- [LUNA-100M](https://huggingface.co/ASTERIZER/LUNA-100M) — 4.5B-token pretrain + RAG/MCP SFT
+- [LUNA-300M](https://huggingface.co/ASTERIZER/LUNA-300M) — 4.5B-token pretrain (2.7× scale-up)
+- LUNA-1B — in progress
+
+**Tokenizer (multilingual BPE)**
+- [LUNA-1B-Tokenizer](https://huggingface.co/ASTERIZER/LUNA-1B-Tokenizer) — 128K / 64K / 8K vocab
+- **2.8× better compression** than GPT-NeoX, **67% fewer tokens** on Indic text (Kannada 7×, Telugu 6×, Tamil 5×)
+- Beats `cl100k_base` on Indic; competitive with Sarvam (34/55 head-to-head wins)