Skip to content

Commit

Permalink
update website
Browse files Browse the repository at this point in the history
  • Loading branch information
souzatharsis committed Jan 24, 2025
1 parent 4f4e91a commit aa0bbbb
Show file tree
Hide file tree
Showing 10 changed files with 43 additions and 82 deletions.
26 changes: 13 additions & 13 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -12,19 +12,19 @@ Please [open an issue](https://github.com/souzatharsis/tamingLLMs/issues) with y

Abstract: *The current discourse around Large Language Models (LLMs) tends to focus heavily on their capabilities while glossing over fundamental challenges. Conversely, this book takes a critical look at the key limitations and implementation pitfalls that engineers and technical leaders encounter when building LLM-powered applications. Through practical Python examples and proven open source solutions, it provides an introductory yet comprehensive guide for navigating these challenges. The focus is on concrete problems with reproducible code examples and battle-tested open source tools. By understanding these pitfalls upfront, readers will be better equipped to build products that harness the power of LLMs while sidestepping their inherent limitations.*

| Chapter | PDF | Podcast | Website | Notebook | Status |
|-------------------------------------------|--------------|--------------|--------------|---------------|----------------------|
| Preface | [pdf](https://docsend.com/view/vdnwucxnpbtzu9pk) | | [html](https://www.tamingllms.com/markdown/preface.html) | N/A | *Ready for Review* |
| About the Book | [pdf](https://docsend.com/view/h9zrk4su559d2mmk) | | [html](https://www.tamingllms.com/markdown/intro.html) | N/A | *Ready for Review* |
| Chapter 1: The Evals Gap | [pdf](https://docsend.com/view/a3s9qk8ix3btaa3u) | [podcast](https://tamingllm.substack.com/p/chapter-1-podcast-the-evals-gap) | [html](https://www.tamingllms.com/notebooks/evals.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/evals.ipynb) | *Ready for Review* |
| Chapter 2: Structured Output| [pdf](https://docsend.com/view/5i88kgvkvtxucj3b) | [podcast](https://tamingllm.substack.com/p/chapter-2-podcast-structured-output) | [html](https://www.tamingllms.com/notebooks/structured_output.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/structured_output.ipynb) | *Ready for Review* |
| Chapter 3: Managing Input Data | [pdf](https://docsend.com/view/dp8b6j8jgpexkvkx) | | [html](https://www.tamingllms.com/notebooks/input.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/input.ipynb) | *Ready for Review* |
| Chapter 4: Safety | [pdf](https://docsend.com/view/xzb3f6fqvy5cjzps) | | [html](https://www.tamingllms.com/notebooks/safety.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/safety.ipynb) | *Ready for Review* |
| Chapter 5: Preference-Based Alignment | [pdf](https://docsend.com/view/fi4z8c4jmzncviwa) | | [html](https://www.tamingllms.com/notebooks/alignment.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/alignment.ipynb) | *Ready for Review* |
| Chapter 6: Local LLMs in Practice | [pdf](https://docsend.com/view/ybbh5nifcazw3bdh) | | [html](https://www.tamingllms.com/notebooks/local.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/local.ipynb) | *Ready for Review* |
| Chapter 7: The Falling Cost Paradox | | | | | WIP |
| Chapter 8: Frontiers | | | | | |
| Appendix A: Tools and Resources | | | | | |
| Chapter | Website | Notebook |
|-------------------------------------------|--------------|---------------|
| Preface | [html](https://www.tamingllms.com/markdown/preface.html) | N/A |
| About the Book | [html](https://www.tamingllms.com/markdown/intro.html) | N/A |
| Chapter 1: The Evals Gap | [html](https://www.tamingllms.com/notebooks/evals.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/evals.ipynb) |
| Chapter 2: Structured Output| [html](https://www.tamingllms.com/notebooks/structured_output.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/structured_output.ipynb) |
| Chapter 3: Managing Input Data | [html](https://www.tamingllms.com/notebooks/input.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/input.ipynb) |
| Chapter 4: Safety | [html](https://www.tamingllms.com/notebooks/safety.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/safety.ipynb) |
| Chapter 5: Preference-Based Alignment | [html](https://www.tamingllms.com/notebooks/alignment.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/alignment.ipynb) |
| Chapter 6: Local LLMs in Practice | [html](https://www.tamingllms.com/notebooks/local.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/local.ipynb) |
| Chapter 7: The Falling Cost Paradox | | |
| Chapter 8: Frontiers | | |
| Appendix A: Tools and Resources | | |

## Citation
[![CC BY-NC-SA 4.0][cc-by-nc-sa-image]][cc-by-nc-sa]
Expand Down
Binary file modified tamingllms/_build/.doctrees/environment.pickle
View file
Binary file not shown.
Binary file modified tamingllms/_build/.doctrees/markdown/toc.doctree
View file
Binary file not shown.
27 changes: 13 additions & 14 deletions tamingllms/_build/html/_sources/markdown/toc.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,20 +16,19 @@ Abstract: *The current discourse around Large Language Models (LLMs) tends to fo

---

(*) *The pdf version is preferred as it contains corrections and side notes.*
| Chapter | PDF | Podcast | Website | Notebook | Status |
|-------------------------------------------|--------------|--------------|--------------|---------------|----------------------|
| Preface | [pdf](https://docsend.com/view/vdnwucxnpbtzu9pk) | | [html](https://www.tamingllms.com/markdown/preface.html) | N/A | *Ready for Review* |
| About the Book | [pdf](https://docsend.com/view/h9zrk4su559d2mmk) | | [html](https://www.tamingllms.com/markdown/intro.html) | N/A | *Ready for Review* |
| Chapter 1: The Evals Gap | [pdf](https://docsend.com/view/a3s9qk8ix3btaa3u) | [podcast](https://tamingllm.substack.com/p/chapter-1-podcast-the-evals-gap) | [html](https://www.tamingllms.com/notebooks/evals.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/evals.ipynb) | *Ready for Review* |
| Chapter 2: Structured Output| [pdf](https://docsend.com/view/5i88kgvkvtxucj3b) | [podcast](https://tamingllm.substack.com/p/chapter-2-podcast-structured-output) | [html](https://www.tamingllms.com/notebooks/structured_output.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/structured_output.ipynb) | *Ready for Review* |
| Chapter 3: Managing Input Data | [pdf](https://docsend.com/view/dp8b6j8jgpexkvkx) | | [html](https://www.tamingllms.com/notebooks/input.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/input.ipynb) | *Ready for Review* |
| Chapter 4: Safety | [pdf](https://docsend.com/view/xzb3f6fqvy5cjzps) | | [html](https://www.tamingllms.com/notebooks/safety.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/safety.ipynb) | *Ready for Review* |
| Chapter 5: Preference-Based Alignment | [pdf](https://docsend.com/view/fi4z8c4jmzncviwa) | | [html](https://www.tamingllms.com/notebooks/alignment.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/alignment.ipynb) | *Ready for Review* |
| Chapter 6: Local LLMs in Practice | [pdf](https://docsend.com/view/ybbh5nifcazw3bdh) | | [html](https://www.tamingllms.com/notebooks/local.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/local.ipynb) | *Ready for Review* |
| Chapter 7: The Falling Cost Paradox | | | | | WIP |
| Chapter 8: Frontiers | | | | | |
| Appendix A: Tools and Resources | | | | | |
| Chapter | Website | Notebook |
|-------------------------------------------|--------------|---------------|
| Preface | [html](https://www.tamingllms.com/markdown/preface.html) | N/A |
| About the Book | [html](https://www.tamingllms.com/markdown/intro.html) | N/A |
| Chapter 1: The Evals Gap | [html](https://www.tamingllms.com/notebooks/evals.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/evals.ipynb) |
| Chapter 2: Structured Output| [html](https://www.tamingllms.com/notebooks/structured_output.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/structured_output.ipynb) |
| Chapter 3: Managing Input Data | [html](https://www.tamingllms.com/notebooks/input.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/input.ipynb) |
| Chapter 4: Safety | [html](https://www.tamingllms.com/notebooks/safety.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/safety.ipynb) |
| Chapter 5: Preference-Based Alignment | [html](https://www.tamingllms.com/notebooks/alignment.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/alignment.ipynb) |
| Chapter 6: Local LLMs in Practice | [html](https://www.tamingllms.com/notebooks/local.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/local.ipynb) |
| Chapter 7: The Falling Cost Paradox | | |
| Chapter 8: Frontiers | | |
| Appendix A: Tools and Resources | | |


[![CC BY-NC-SA 4.0][cc-by-nc-sa-image]][cc-by-nc-sa]
Expand Down
37 changes: 0 additions & 37 deletions tamingllms/_build/html/markdown/toc.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -239,94 +239,57 @@ <h1><a class="reference external" href="https://www.tamingllms.com">Taming LLMs<
<h2><em>A Practical Guide to LLM Pitfalls with Open Source Software</em><a class="headerlink" href="#a-practical-guide-to-llm-pitfalls-with-open-source-software" title="Permalink to this heading"></a></h2>
<p>Abstract: <em>The current discourse around Large Language Models (LLMs) tends to focus heavily on their capabilities while glossing over fundamental challenges. Conversely, this book takes a critical look at the key limitations and implementation pitfalls that engineers and technical leaders encounter when building LLM-powered applications. Through practical Python examples and proven open source solutions, it provides an introductory yet comprehensive guide for navigating these challenges. The focus is on concrete problems with reproducible code examples and battle-tested open source tools. By understanding these pitfalls upfront, readers will be better equipped to build products that harness the power of LLMs while sidestepping their inherent limitations.</em></p>
<hr class="docutils" />
<p>(*) <em>The pdf version is preferred as it contains corrections and side notes.</em></p>
<table class="docutils align-default">
<thead>
<tr class="row-odd"><th class="head"><p>Chapter</p></th>
<th class="head"><p>PDF</p></th>
<th class="head"><p>Podcast</p></th>
<th class="head"><p>Website</p></th>
<th class="head"><p>Notebook</p></th>
<th class="head"><p>Status</p></th>
</tr>
</thead>
<tbody>
<tr class="row-even"><td><p>Preface</p></td>
<td><p><a class="reference external" href="https://docsend.com/view/vdnwucxnpbtzu9pk">pdf</a></p></td>
<td><p></p></td>
<td><p><a class="reference external" href="https://www.tamingllms.com/markdown/preface.html">html</a></p></td>
<td><p>N/A</p></td>
<td><p><em>Ready for Review</em></p></td>
</tr>
<tr class="row-odd"><td><p>About the Book</p></td>
<td><p><a class="reference external" href="https://docsend.com/view/h9zrk4su559d2mmk">pdf</a></p></td>
<td><p></p></td>
<td><p><a class="reference external" href="https://www.tamingllms.com/markdown/intro.html">html</a></p></td>
<td><p>N/A</p></td>
<td><p><em>Ready for Review</em></p></td>
</tr>
<tr class="row-even"><td><p>Chapter 1: The Evals Gap</p></td>
<td><p><a class="reference external" href="https://docsend.com/view/a3s9qk8ix3btaa3u">pdf</a></p></td>
<td><p><a class="reference external" href="https://tamingllm.substack.com/p/chapter-1-podcast-the-evals-gap">podcast</a></p></td>
<td><p><a class="reference external" href="https://www.tamingllms.com/notebooks/evals.html">html</a></p></td>
<td><p><a class="reference external" href="https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/evals.ipynb">ipynb</a></p></td>
<td><p><em>Ready for Review</em></p></td>
</tr>
<tr class="row-odd"><td><p>Chapter 2: Structured Output</p></td>
<td><p><a class="reference external" href="https://docsend.com/view/5i88kgvkvtxucj3b">pdf</a></p></td>
<td><p><a class="reference external" href="https://tamingllm.substack.com/p/chapter-2-podcast-structured-output">podcast</a></p></td>
<td><p><a class="reference external" href="https://www.tamingllms.com/notebooks/structured_output.html">html</a></p></td>
<td><p><a class="reference external" href="https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/structured_output.ipynb">ipynb</a></p></td>
<td><p><em>Ready for Review</em></p></td>
</tr>
<tr class="row-even"><td><p>Chapter 3: Managing Input Data</p></td>
<td><p><a class="reference external" href="https://docsend.com/view/dp8b6j8jgpexkvkx">pdf</a></p></td>
<td><p></p></td>
<td><p><a class="reference external" href="https://www.tamingllms.com/notebooks/input.html">html</a></p></td>
<td><p><a class="reference external" href="https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/input.ipynb">ipynb</a></p></td>
<td><p><em>Ready for Review</em></p></td>
</tr>
<tr class="row-odd"><td><p>Chapter 4: Safety</p></td>
<td><p><a class="reference external" href="https://docsend.com/view/xzb3f6fqvy5cjzps">pdf</a></p></td>
<td><p></p></td>
<td><p><a class="reference external" href="https://www.tamingllms.com/notebooks/safety.html">html</a></p></td>
<td><p><a class="reference external" href="https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/safety.ipynb">ipynb</a></p></td>
<td><p><em>Ready for Review</em></p></td>
</tr>
<tr class="row-even"><td><p>Chapter 5: Preference-Based Alignment</p></td>
<td><p><a class="reference external" href="https://docsend.com/view/fi4z8c4jmzncviwa">pdf</a></p></td>
<td><p></p></td>
<td><p><a class="reference external" href="https://www.tamingllms.com/notebooks/alignment.html">html</a></p></td>
<td><p><a class="reference external" href="https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/alignment.ipynb">ipynb</a></p></td>
<td><p><em>Ready for Review</em></p></td>
</tr>
<tr class="row-odd"><td><p>Chapter 6: Local LLMs in Practice</p></td>
<td><p><a class="reference external" href="https://docsend.com/view/ybbh5nifcazw3bdh">pdf</a></p></td>
<td><p></p></td>
<td><p><a class="reference external" href="https://www.tamingllms.com/notebooks/local.html">html</a></p></td>
<td><p><a class="reference external" href="https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/local.ipynb">ipynb</a></p></td>
<td><p><em>Ready for Review</em></p></td>
</tr>
<tr class="row-even"><td><p>Chapter 7: The Falling Cost Paradox</p></td>
<td><p></p></td>
<td><p></p></td>
<td><p></p></td>
<td><p></p></td>
<td><p>WIP</p></td>
</tr>
<tr class="row-odd"><td><p>Chapter 8: Frontiers</p></td>
<td><p></p></td>
<td><p></p></td>
<td><p></p></td>
<td><p></p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p>Appendix A: Tools and Resources</p></td>
<td><p></p></td>
<td><p></p></td>
<td><p></p></td>
<td><p></p></td>
<td><p></p></td>
</tr>
</tbody>
</table>
Expand Down
2 changes: 1 addition & 1 deletion tamingllms/_build/html/searchindex.js
View file

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion tamingllms/_build/jupyter_execute/markdown/intro.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "markdown",
"id": "87ed3c40",
"id": "789163a3",
"metadata": {},
"source": [
"(intro)=\n",
Expand Down
2 changes: 1 addition & 1 deletion tamingllms/latex/chapters/alignment.tex
View file
Original file line number Diff line number Diff line change
Expand Up @@ -723,7 +723,7 @@ \subsection{User Prompts}
\subsection{Rejected Responses}


We create sample rejected responses from an unaligned base model, which here we use\texttt{SmolLM2-360M-Instruct}~\sidenote[][*1]{
We create sample rejected responses from an unaligned base model, which here we use \texttt{SmolLM2-360M-Instruct}~\sidenote[][*1]{
The \texttt{ResponseGenerator} class creates a dataset of responses from an unaligned base model that we aim to improve through fine-tuning. These responses serve as ``rejected'' examples in our training data since they may not properly align with safety policies and guidelines. The class supports both local model inference using the Hugging Face Transformers library and remote inference through the Hugging Face Inference API. When instantiated with a model name, it loads the model locally. Otherwise, if a cloud API URL is provided, it connects to the remote API endpoint for inference.
}.

Expand Down
2 changes: 1 addition & 1 deletion tamingllms/latex/chapters/safety.tex
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1136,7 +1136,7 @@ \subsubsection{LLM-Based Safety Filtering}
\label{granite}
\end{figure}

The industry is increasingly focusing on the fine-tuning of pre-trained base models targeting a specific dimension of requirements and standards, here Safety being a critical one. This trend encompasses the release of open-source, fine-tuned safety models that can act as protective guardrails for LLM applications, as exemplified by LLaMa-Guard and IBM Granite Guardian. Additionally, there is a notable rise in models fine-tuned through techniques such as Reinforcement Learning from Human Feedback (RLHF), utilizing human preference datasets that incorporate safety considerations. These specialized models can function as safety filters as discussed but also as main models that alone could accomplished their original intended task safely without the need of external filters. We will cover this specific topic in the Chapter \ref{alignment}, where we will explore the process of aligning language models with human preferences ultimately leading to the development of an open source fine-tuned model that complies with user provided policy-based requirements.
The industry is increasingly focusing on the fine-tuning of pre-trained base models targeting a specific dimension of requirements and standards, here Safety being a critical one. This trend encompasses the release of open-source, fine-tuned safety models that can act as protective guardrails for LLM applications, as exemplified by LLaMa-Guard and IBM Granite Guardian. Additionally, there is a notable rise in models fine-tuned through techniques such as Reinforcement Learning from Human Feedback (RLHF), utilizing human preference datasets that incorporate safety considerations. These specialized models can function as safety filters as discussed but also as main models that alone could accomplished their original intended task safely without the need of external filters. We will cover this specific topic in the Chapter \ref{chapter:alignment}, where we will explore the process of aligning language models with human preferences ultimately leading to the development of an open source fine-tuned model that complies with user provided policy-based requirements.

\subsection{Custom Moderation}
\label{custom-moderation}
Expand Down
Loading

0 comments on commit aa0bbbb

Please sign in to comment.