From de0ec1fba26f728e188bd78755d63f459b132448 Mon Sep 17 00:00:00 2001
From: Morteza Hosseini <s_morteza_h@yahoo.com>
Date: Mon, 13 May 2024 21:22:22 +0100
Subject: [PATCH] Update README.md and add tokenization article for LLMs

---
 README.md              | 16 ++++++++++------
 llm/tokenization.ipynb |  2 +-
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/README.md b/README.md
index d5b975ce..560c20dd 100644
--- a/README.md
+++ b/README.md
@@ -25,6 +25,12 @@ In addition to these projects, I regularly share my insights and learnings on th
 - [Understanding Hashing](data-structure/hashing.ipynb): Dive into the world of hashing, its applications, and Python implementation.
 - [Sorting Algorithms](data-structure/sorting-popular.ipynb): A comprehensive guide to understanding and implementing popular sorting algorithms in Python.
 
+## :art: Data Visualization
+
+- [lets-plot](visualization/lets-plot/codebook.ipynb): Create stunning plots with [lets-plot](https://lets-plot.org/index.html), a Python port of the R's [ggplot2](https://ggplot2.tidyverse.org/) library.
+- [Pitfalls](visualization/pitfalls/pitfalls.ipynb): Avoid common pitfalls in data visualization.
+- [QR Code](visualization/qrcode.ipynb): Generate QR codes with ease.
+
 ## :mag: EDA (Exploratory Data Analysis)
 
 - [Data Balancing](eda/data-balancing.ipynb): Learn techniques to balance imbalanced datasets.
@@ -40,6 +46,10 @@ In addition to these projects, I regularly share my insights and learnings on th
 - [KerasTuner](hypertune/kerasTuner.ipynb): Optimize your models with hyperparameter tuning using the [KerasTuner](https://keras.io/keras_tuner/) library.
 - [Optuna](hypertune/optuna.ipynb): Enhance your models with hyperparameter tuning using the [Optuna](https://optuna.org/) library.
 
+## :brain: LLM (Large Language Model)
+
+- [Tokenization](llm/tokenization.ipynb): Explore the tokenization of text data.
+
 ## :robot: Machine Learning
 
 - [Best Threshold for Logistic Regression](machine-learning/threshold-logistic-regression.ipynb): Explore different methods to find the optimal threshold for logistic regression.
@@ -76,12 +86,6 @@ In addition to these projects, I regularly share my insights and learnings on th
 - [Forecasting with sktime](time-series/sktime.ipynb): Forecast time-series data using the [sktime](https://github.com/sktime/sktime) library.
 - [Prevent Overfitting](time-series/prevent-overfitting.ipynb): Learn techniques to prevent overfitting in time series forecasting.
 
-## :art: Data Visualization
-
-- [lets-plot](visualization/lets-plot/codebook.ipynb): Create stunning plots with [lets-plot](https://lets-plot.org/index.html), a Python port of the R's [ggplot2](https://ggplot2.tidyverse.org/) library.
-- [Pitfalls](visualization/pitfalls/pitfalls.ipynb): Avoid common pitfalls in data visualization.
-- [QR Code](visualization/qrcode.ipynb): Generate QR codes with ease.
-
 ## :spider_web: Web Scraping
 
 - [jobinventory](scrape/jobinventory.com/tutorial.ipynb): Scrape job listings from jobinventory.com using Python.
diff --git a/llm/tokenization.ipynb b/llm/tokenization.ipynb
index 32354956..53db2914 100644
--- a/llm/tokenization.ipynb
+++ b/llm/tokenization.ipynb
@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Click [here]() to access the associated Medium article."
+    "Click [here](https://morihosseini.medium.com/from-characters-to-context-tokenization-in-llms-09b20abc42ed) to access the associated Medium article."
    ]
   },
   {