*** next steps

gbenson · May 16, 2024 · 87543c0 · 87543c0
1 parent e4d4c12
commit 87543c0
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 5 deletions.
diff --git a/README.md b/README.md
@@ -9,8 +9,7 @@
 
 # DOM tokenizers
 
-DOM-aware tokenizers for [🤗 Hugging Face](https://huggingface.co/)
-language models.
+DOM-aware tokenizers for Hugging Face language models.
 
 ## Installation
 
@@ -30,7 +29,9 @@ 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
@@ -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",