From 4734b680d7c9480b662f3cca1e49c6e1dc78d660 Mon Sep 17 00:00:00 2001
From: Gary Benson <gary@gbenson.net>
Date: Thu, 16 May 2024 01:02:24 +0100
Subject: [PATCH] *** next steps

---
 README.md      | 6 ++++--
 pyproject.toml | 4 ++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index b809b48..da316cd 100644
--- a/README.md
+++ b/README.md
@@ -9,7 +9,7 @@
 
 # DOM tokenizers
 
-DOM-aware tokenizers for [🤗 Hugging Face](https://huggingface.co/)
+DOM-aware tokenizers for [Hugging Face](https://huggingface.co/)
 language models.
 
 ## Installation
@@ -30,7 +30,9 @@ pip install --upgrade pip
 pip install -e .[dev,train]
 ```
 
-## Train a tokenizer
+## Load a pretrained tokenizer from the Hub
+
+## Train your own
 ```sh
 train-tokenizer gbenson/interesting-dom-snapshots -n 10000
 ```
diff --git a/pyproject.toml b/pyproject.toml
index 6b73303..ccc9d7e 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -2,9 +2,9 @@
 name = "dom-tokenizers"
 version = "0.0.2"
 authors = [{ name = "Gary Benson" }]
-description = "DOM-aware tokenizers for Hugging Face language models"
+description = "DOM-aware tokenizers for 🤗 Hugging Face language models"
 readme = "README.md"
-license = { text = "Apache Software License (Apache-2.0)" }
+license = { text = "Apache-2.0" }
 requires-python = ">=3.10"  # match..case
 classifiers = [
     "Development Status :: 4 - Beta",