From b0b25911de49770bf6321d8b77205db0ed0edfa4 Mon Sep 17 00:00:00 2001
From: Qubitium-ModelCloud <qubitium@modelcloud.ai>
Date: Fri, 21 Feb 2025 15:16:20 +0800
Subject: [PATCH] prepare for 0.0.3 release (#29)

* prepare for 0.0.3 release

* Update README.md
---
 README.md | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/README.md b/README.md
index 925ecbf..9eac0f2 100644
--- a/README.md
+++ b/README.md
@@ -9,6 +9,8 @@
 </p>
 
 ## News
+* 02/21/2025 [0.0.3](https://github.com/ModelCloud/Tokenicer/releases/tag/v0.0.3): Now `tokenicer` instance dynamically inherits the `native` `tokenizer.__class__` of tokenizer passed in or loaded via our `tokenicer.load()` api.
+
 * 02/10/2025 [0.0.2](https://github.com/ModelCloud/Tokenicer/releases/tag/v0.0.2): 🤗 Initial release!
 
 ## Features:
@@ -52,10 +54,13 @@ pip install -v .
 
 # With `Tokenicer.load()`
 from tokenicer import Tokenicer
+
+# Returns `Tokenicer` instance that inherits original `Qwen2TokenizerFast` type.
 tokenizer = Tokenicer.load('Qwen/Qwen2.5-0.5B-Instruct')
 
 # That's it! Toke(n)icer has auto-fixed Qwen2.5-0.5B-Instruct's incorrect `pad_token`.
 # Now this this model can be `trained` and `inferenced` correctly with `batch` and `masks`.
+# Now use the new tokenizer like any normal HF PretrainedTokenizer(Fast)
 print(f"pad_token: `{tokenizer.pad_token}`")
 ```