Add model card README

README.md

@@ -0,0 +1,58 @@
+---
+tags:
+- tokie
+library_name: tokie
+---
+
+<p align="center">
+  <img src="tokie-banner.png" alt="tokie" width="600">
+</p>
+
+# phi-2
+
+Pre-built [tokie](https://github.com/chonkie-inc/tokie) tokenizer for [microsoft/phi-2](https://huggingface.co/microsoft/phi-2).
+
+## Quick Start (Python)
+
+```bash
+pip install tokie
+```
+
+```python
+import tokie
+
+tokenizer = tokie.Tokenizer.from_pretrained("tokiers/phi-2")
+encoding = tokenizer.encode("Hello, world!")
+print(encoding.ids)
+print(encoding.attention_mask)
+```
+
+## Quick Start (Rust)
+
+```toml
+[dependencies]
+tokie = { version = "0.0.4", features = ["hf"] }
+```
+
+```rust
+use tokie::Tokenizer;
+
+let tokenizer = Tokenizer::from_pretrained("tokiers/phi-2").unwrap();
+let encoding = tokenizer.encode("Hello, world!", true);
+println!("{:?}", encoding.ids);
+```
+
+## Files
+
+- `tokenizer.tkz` — tokie binary format (~10x smaller, loads in ~5ms)
+- `tokenizer.json` — original HuggingFace tokenizer
+
+## About tokie
+
+**50x faster tokenization, 10x smaller model files, 100% accurate.**
+
+tokie is a drop-in replacement for HuggingFace tokenizers, built in Rust. See [GitHub](https://github.com/chonkie-inc/tokie) for benchmarks and documentation.
+
+## License
+
+MIT OR Apache-2.0 (tokie library). Original model files retain their original license from [microsoft/phi-2](https://huggingface.co/microsoft/phi-2).