From e827b42e1e82fee28fd25f37765680664e35cd76 Mon Sep 17 00:00:00 2001
From: rasbt <mail@sebastianraschka.com>
Date: Wed, 25 Oct 2023 18:46:40 -0500
Subject: [PATCH] add readme files

---
 ch01/README.md                              | 3 ++-
 ch02/01_main-chapter-code/README.md         | 5 +++++
 ch02/02_bonus_bytepair-encoder/README.md    | 7 +++++++
 ch02/03_bonus_embedding-vs-matmul/README.md | 3 +++
 ch02/README.md                              | 7 +++++++
 5 files changed, 24 insertions(+), 1 deletion(-)
 create mode 100644 ch02/01_main-chapter-code/README.md
 create mode 100644 ch02/02_bonus_bytepair-encoder/README.md
 create mode 100644 ch02/03_bonus_embedding-vs-matmul/README.md
 create mode 100644 ch02/README.md

diff --git a/ch01/README.md b/ch01/README.md
index 1e7ac0c..50002e6 100644
--- a/ch01/README.md
+++ b/ch01/README.md
@@ -1,2 +1,3 @@
-Details will follow ...
+# Chapter 1: Understanding Large Language Models
 
+There is no code in this chapter.
diff --git a/ch02/01_main-chapter-code/README.md b/ch02/01_main-chapter-code/README.md
new file mode 100644
index 0000000..646bf68
--- /dev/null
+++ b/ch02/01_main-chapter-code/README.md
@@ -0,0 +1,5 @@
+# Chapter 2: Working with Text Data
+
+- [ch02.ipynb](ch02.ipynb) has all the code as it appears in the chapter
+- [dataloader.ipynb](dataloader.ipynb) is a minimal notebook with the main data loading pipeline implemented in this chapter
+
diff --git a/ch02/02_bonus_bytepair-encoder/README.md b/ch02/02_bonus_bytepair-encoder/README.md
new file mode 100644
index 0000000..30a1946
--- /dev/null
+++ b/ch02/02_bonus_bytepair-encoder/README.md
@@ -0,0 +1,7 @@
+# Chapter 2: Working with Text Data
+
+
+
+- [compare-bpe-tiktoken.ipynb](compare-bpe-tiktoken.ipynb) benchmarks various byte pair encoding implementations
+- [bpe_openai_gpt2.py](bpe_openai_gpt2.py) is the original bytepair encoder code used by OpenAI
+
diff --git a/ch02/03_bonus_embedding-vs-matmul/README.md b/ch02/03_bonus_embedding-vs-matmul/README.md
new file mode 100644
index 0000000..a1f67ef
--- /dev/null
+++ b/ch02/03_bonus_embedding-vs-matmul/README.md
@@ -0,0 +1,3 @@
+# Chapter 2: Working with Text Data
+
+- [embeddings-and-linear-layers.ipynb](embeddings-and-linear-layers.ipynb) contains optional (bonus) code to explain that embedding layers and fully connected layers applied to one-hot encoded vectors are equivalent.
diff --git a/ch02/README.md b/ch02/README.md
new file mode 100644
index 0000000..7c085a9
--- /dev/null
+++ b/ch02/README.md
@@ -0,0 +1,7 @@
+# Chapter 2: Working with Text Data
+
+- [01_main-chapter-code](01_main-chapter-code) contains the main chapter code
+  
+- [02_bonus_bytepair-encoder](02_bonus_bytepair-encoder) contains optional code to benchmark different byte pair encoder implementations
+  
+- [03_bonus_embedding-vs-matmul](03_bonus_embedding-vs-matmul) contains optional (bonus) code to explain that embedding layers and fully connected layers applied to one-hot encoded vectors are equivalent.