Skip to content

Commit

Permalink
Built site for gh-pages
Browse files Browse the repository at this point in the history
  • Loading branch information
@dhavala
dhavala committed Nov 11, 2024
1 parent 3d470fb commit 0fade7c
Show file tree
Hide file tree
Showing 6 changed files with 104 additions and 34 deletions.
2 changes: 1 addition & 1 deletion .nojekyll
View file
Original file line number Diff line number Diff line change
@@ -1 +1 @@
a4c0ee43
29e08d80
75 changes: 58 additions & 17 deletions lectures/w13-l01.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -416,28 +416,80 @@ <h3 class="anchored" data-anchor-id="in-class">In-Class</h3>
<li>Datasets and Tasks (to train LLMs)
<ul>
<li><a href="https://lcs2-iitd.github.io/ELL881-AIL821-2401/static_files/presentations/71.pdf">Lecture 7 from AIL821</a></li>
</ul></li>
<li>Model Training
<ul>
<li>Pre-training
<ul>
<li><a href="https://lcs2-iitd.github.io/ELL881-AIL821-2401/static_files/presentations/121.pdf">Lecture 12.1 from AIL821</a></li>
</ul></li>
<li>Alignment
<ul>
<li><a href="https://arxiv.org/abs/2305.18290">Direct Preference Optimization: Your Language Model is Secretly a Reward Model</a></li>
</ul></li>
<li>Fine-tuning
<ul>
<li><a href="https://arxiv.org/abs/2106.09685">LoRA: Low-Rank Adaptation of Large Language Models</a></li>
</ul></li>
</ul></li>
<li>Prompt Optimization
<ul>
<li><a href="https://arxiv.org/abs/2201.11903">Chain-of-Thought</a></li>
</ul></li>
<li>Constrained Language Generation
<ul>
<li><a href="https://github.com/Saibo-creator/Awesome-LLM-Constrained-Decoding">Collection</a></li>
</ul></li>
<li>Evaluation
<ul>
<li><a href="https://llm-class.github.io/slides/Yann_Dubois.pdf">Scaling Evaluation of LLMs</a> Yann Bubois, CIS 7000 LLM Course</li>
</ul></li>
<li>Applications and Design Patterns
<ul>
<li>Tools
<ul>
<li><a href="https://gorilla.cs.berkeley.edu/">Gorilla</a></li>
</ul></li>
<li>Agents
<ul>
<li>Lilian Wang’s blog on <a href="https://lilianweng.github.io/posts/2023-06-23-agent/">LLM Powered Autonomous Agents</a></li>
<li>Aman’s blog on <a href="https://aman.ai/primers/ai/agents/">Agents</a></li>
</ul></li>
<li>RAG
<ul>
<li>Paper from NVidia <a href="https://arxiv.org/abs/2407.07858">FACTS About Building Retrieval Augmented Generation-based Chatbots</a></li>
</ul></li>
</ul></li>
<li>LLMs can not reason &amp; plan
<ul>
<li><a href="https://arxiv.org/abs/2402.01817">LLMs Can’t Plan, But Can Help Planning in LLM-Modulo Frameworks</a></li>
</ul></li>
</ol>
</section>
<section id="post-class" class="level3">
<h3 class="anchored" data-anchor-id="post-class">Post-class</h3>
<ol type="1">
<li>Datasets and Tasks (to train LLMs)
<ul>
<li><a href="https://arxiv.org/abs/2305.11206">LIMA: less is more for alignment</a></li>
<li><a href="https://arxiv.org/pdf/2308.10792">Instruction Tuning for Large Language Models: A Survey</a></li>
<li><a href="https://allenai.org/olmo">OLMo @ Allen AI</a></li>
<li><a href="https://allenai.org/olmo">OLMo @ Allen AI</a> - if you are interesting in all aspects of open-source LLM development.</li>
</ul></li>
<li>Model Training
<ul>
<li>Pre-training
<ul>
<li><a href="https://lcs2-iitd.github.io/ELL881-AIL821-2401/static_files/presentations/121.pdf">Lecture 12.1 from AIL821</a></li>
<li><a href="https://hayate-lab.com/wp-content/uploads/2023/05/43372bfa750340059ad87ac8e538c53b.pdf">Improving Language Understanding by Generative Pre-Training</a></li>
</ul></li>
<li>Alignment
<ul>
<li><a href="https://lcs2-iitd.github.io/ELL881-AIL821-2401/static_files/presentations/121.pdf">Lecture 12.2 from AIL821</a></li>
<li><a href="https://arxiv.org/abs/2305.18290">Direct Preference Optimization: Your Language Model is Secretly a Reward Model</a></li>
</ul></li>
<li>Fine-tuning
<ul>
<li>Performance Efficient Fine-Tuning <a href="https://github.com/huggingface/peft">collection</a></li>
<li>Lecture: <a href="https://lcs2-iitd.github.io/ELL881-AIL821-2401/static_files/presentations/141.pdf">PEFT</a></li>
<li>Lecture: : <a href="https://lcs2-iitd.github.io/ELL881-AIL821-2401/static_files/presentations/142.pdf">Quantization and Pruning</a></li>
<li><a href="https://arxiv.org/abs/2106.09685">LoRA: Low-Rank Adaptation of Large Language Models</a></li>
<li><a href="https://arxiv.org/abs/2305.14314">QLoRA: Efficient Finetuning of Quantized LLMs</a></li>
</ul></li>
</ul></li>
Expand All @@ -463,12 +515,10 @@ <h3 class="anchored" data-anchor-id="in-class">In-Class</h3>
<ul>
<li>Tools
<ul>
<li><a href="https://gorilla.cs.berkeley.edu/">Gorilla</a></li>
<li>[Lecture 18.2 from AIL821] <a href="https://lcs2-iitd.github.io/ELL881-AIL821-2401/static_files/presentations/172.pdf">LLMs and Tools: Function Calling</a></li>
</ul></li>
<li>Agents
<ul>
<li>Lilian Wang’s blog on <a href="https://lilianweng.github.io/posts/2023-06-23-agent/">LLM Powered Autonomous Agents</a></li>
<li>[Lecture 18.3 from AIL821] <a href="https://lcs2-iitd.github.io/ELL881-AIL821-2401/static_files/presentations/173.pdf">LLMs and Tools: Agentic</a></li>
<li>AutoGen <a href="https://github.com/microsoft/autogen">repo</a></li>
<li>CrewAI <a href="https://github.com/crewAIInc/crewAI">repo</a></li>
Expand All @@ -477,28 +527,18 @@ <h3 class="anchored" data-anchor-id="in-class">In-Class</h3>
</ul></li>
<li>RAG
<ul>
<li>Paper from NVidia <a href="https://arxiv.org/abs/2407.07858">FACTS About Building Retrieval Augmented Generation-based Chatbots</a></li>
<li><a href="https://arxiv.org/abs/2312.10997">Retrieval-Augmented Generation for Large Language Models: A Survey</a> Mar’24</li>
<li><a href="https://arxiv.org/abs/2407.01219">Searching for Best Practices in Retrieval-Augmented Generation</a> Jul’24</li>
</ul></li>
</ul></li>
<li>LLMs can not reason &amp; plan
<ul>
<li>Lecture 19 from AIL821 <a href="https://lcs2-iitd.github.io/ELL881-AIL821-2401/static_files/presentations/181.pdf">Reasoning in LLMs</a></li>
<li><a href="https://arxiv.org/abs/2402.01817">LLMs Can’t Plan, But Can Help Planning in LLM-Modulo Frameworks</a></li>
<li><a href="https://arxiv.org/abs/2410.05229v1">GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models</a></li>
<li><a href="https://openai.com/index/learning-to-reason-with-llms/">Learning to reason with LLMs</a></li>
<li><a href="https://github.com/open-thought/system-2-research">Systems-2 Collection Repo</a></li>
</ul></li>
</ol>
</section>
<section id="post-class" class="level3">
<h3 class="anchored" data-anchor-id="post-class">Post-class</h3>
<ul>
<li>Other modules in AIL821 <a href="https://lcs2-iitd.github.io/ELL881-AIL821-2401/">LLMs Course</a> @ IIT-D</li>
<li>Advanced topics in CIS 7000 <a href="https://llm-class.github.io/">LLM Course</a></li>
<li>Walk through the book <a href="https://github.com/rasbt/LLMs-from-scratch">Building LLMs from Scratch</a></li>
</ul>
<section id="llms-and-influence-functions" class="level4">
<h4 class="anchored" data-anchor-id="llms-and-influence-functions">LLMs and Influence Functions</h4>
<ol type="1">
Expand All @@ -510,9 +550,10 @@ <h4 class="anchored" data-anchor-id="llms-and-influence-functions">LLMs and Infl
<section id="full-courses" class="level4">
<h4 class="anchored" data-anchor-id="full-courses">Full Courses</h4>
<ol type="1">
<li>CIS7000 <a href="https://llm-class.github.io/">LLM Course</a> @ UPenn by Prof.&nbsp;Mayur Naik. Covers many advanced topics</li>
<li>CIS7000 <a href="https://llm-class.github.io/">LLM Course</a> @ UPenn by Prof.&nbsp;Mayur Naik. Covers many advanced topics.</li>
<li>AIL821 <a href="https://lcs2-iitd.github.io/ELL881-AIL821-2401/">LLMs Course</a> @ IIT-D</li>
<li><a href="https://www.shane.st/teaching/574/spr24/">Deep Learning For NLP @ UW</a> LING 574, Deep Learning For NLP, Prof.&nbsp;Shane @ UW, Spring’24.</li>
<li>Walk through the book <a href="https://github.com/rasbt/LLMs-from-scratch">Building LLMs from Scratch</a></li>
</ol>


Expand Down
3 changes: 2 additions & 1 deletion lectures/w13-l02.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -429,6 +429,7 @@ <h3 class="anchored" data-anchor-id="in-class">In-Class</h3>
<ul>
<li>with LangGraph <a href="https://langchain-ai.github.io/langgraph/tutorials/">tutorials</a></li>
<li><a href="https://medium.com/@lorevanoudenhove/how-to-build-ai-agents-with-langgraph-a-step-by-step-guide-5d84d9c7e832">blog</a> explaining LangGraph</li>
<li><a href="https://github.com/microsoft/autogen/tree/main/python/packages/autogen-magentic-one">Magentic-One</a></li>
</ul></li>
</ol>
</section>
Expand All @@ -438,7 +439,7 @@ <h3 class="anchored" data-anchor-id="post-class">Post-class</h3>
<li>Training with <a href="https://docs.ray.io/en/latest/train/train.html">Ray Train</a></li>
<li>Serving with <a href="https://docs.ray.io/en/latest/serve/index.html">Ray Serve</a>, <a href="https://docs.vllm.ai/en/latest/">vLLM</a>, <a href="https://ollama.com/">ollama</a> for serving</li>
<li>RAGs with <a href="https://www.llamaindex.ai/">Llamaindex</a>, <a href="https://www.truefoundry.com/cognita">cognita</a>, <a href="https://www.langchain.com/">Langchain</a></li>
<li>Agens with <a href="https://www.langchain.com/langgraph">LangGraph</a>, <a href="https://github.com/microsoft/autogen">AutoGen</a>, <a href="https://github.com/crewAIInc/crewAI">CrewAI</a>, LangGraph IDE <a href="https://blog.langchain.dev/langgraph-studio-the-first-agent-ide/">blog</a></li>
<li>Agents with <a href="https://www.langchain.com/langgraph">LangGraph</a>, <a href="https://github.com/microsoft/autogen">AutoGen</a>, <a href="https://github.com/crewAIInc/crewAI">CrewAI</a>, LangGraph IDE <a href="https://blog.langchain.dev/langgraph-studio-the-first-agent-ide/">blog</a></li>
</ul>


Expand Down
46 changes: 37 additions & 9 deletions lectures/w13-l03.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -359,8 +359,7 @@ <h2 id="toc-title">Table of contents</h2>
<li><a href="#materials" id="toc-materials" class="nav-link active" data-scroll-target="#materials">Materials:</a>
<ul class="collapse">
<li><a href="#pre-work" id="toc-pre-work" class="nav-link" data-scroll-target="#pre-work">Pre-work:</a></li>
<li><a href="#in-class" id="toc-in-class" class="nav-link" data-scroll-target="#in-class">In-Class</a></li>
<li><a href="#post-class" id="toc-post-class" class="nav-link" data-scroll-target="#post-class">Post-class</a></li>
<li><a href="#ml-engineering" id="toc-ml-engineering" class="nav-link" data-scroll-target="#ml-engineering">ML Engineering</a></li>
</ul></li>
</ul>
<div class="toc-actions"><ul><li><a href="https://github.com/mlsquare/ai-839/edit/main/lectures/w13-l03.qmd" class="toc-action"><i class="bi bi-github"></i>Edit this page</a></li><li><a href="https://github.com/mlsquare/ai-839/issues/new" class="toc-action"><i class="bi empty"></i>Report an issue</a></li></ul></div></nav>
Expand Down Expand Up @@ -395,15 +394,44 @@ <h3 class="anchored" data-anchor-id="pre-work">Pre-work:</h3>
<ol type="1">
<li><a href="../lectures/w13-l01.html">LLM Intro</a></li>
<li><a href="../lectures/w13-l02.html">LLM Ops</a></li>
<li><a href="https://explainml-tutorial.github.io/">XAI Tutorial</a> by Hima Lakkaraju, Julius Adebayo, Sameer Singh</li>
<li><a href="https://www.gatsby.ucl.ac.uk/~balaji/balaji-uncertainty-talk-cifar-dlrl.pdf">UQ Tutorial</a> by Balaji Lakshminarayanan</li>
</ol>
</section>
<section id="in-class" class="level3">
<h3 class="anchored" data-anchor-id="in-class">In-Class</h3>
<p>tbd</p>
</section>
<section id="post-class" class="level3">
<h3 class="anchored" data-anchor-id="post-class">Post-class</h3>
<p>tbd</p>
<section id="ml-engineering" class="level3">
<h3 class="anchored" data-anchor-id="ml-engineering">ML Engineering</h3>
<ul>
<li><a href="https://github.com/meta-llama/llama-stack">LLaMA Stack</a> - a full stack LLaMA-centered APIs for inference, safety, agentic system, among others.</li>
<li><a href="https://mlflow.org/docs/latest/llms/index.html">MLFlow LLMs</a> - tool calling, agents, evaluation, RAGs, serving and more</li>
<li><a href="https://github.com/ray-project/ray-llm">Ray LLMs</a></li>
<li><a href="https://mlflow.org/docs/latest/llms/tracing/index.html">MLFlow Tracing</a> observability for LLMs</li>
<li>Others popular stacks <a href="https://www.llamaindex.ai/">LlamaIndex</a>, <a href="https://www.langchain.com/">LangChain</a></li>
<li><a href="https://github.com/confident-ai/deepeval">DeepEval</a></li>
</ul>
<p>XAI</p>
<ul>
<li>XAI @ Harvard, Spring’23, <a href="https://interpretable-ml-class.github.io/">Explainable AI</a> by Prof.Hima Lakkaraju</li>
<li>Publications by <a href="https://himalakkaraju.github.io/">Hima Lakkaraju</a></li>
<li>LLMs for XAI
<ul>
<li><a href="https://arxiv.org/abs/2401.13110">Can Large Language Models Simplify Explainable AI</a></li>
</ul></li>
<li>XAI for LLMs
<ul>
<li><a href="https://arxiv.org/abs/2308.03296">Studying Large Language Model Generalization with Influence Functions</a></li>
<li><a href="https://arxiv.org/abs/2409.19998">Do Influence Functions Work on Large Language Models?</a></li>
</ul></li>
</ul>
<p>UQ</p>
<ul>
<li><a href="https://arxiv.org/abs/2311.03533">Quantifying Uncertainty in Natural Language Explanations of Large Language Models</a></li>
<li><a href="https://arxiv.org/abs/2305.18404">Conformal Prediction with Large Language Models for Multi-Choice Question Answering</a> <a href="https://github.com/bhaweshiitk/ConformalLLM">code</a></li>
</ul>
<p>Security</p>
<ul>
<li><a href="https://github.com/NVIDIA/NeMo-Guardrails">NeMO Gaurdrails</a></li>
<li><a href="https://huggingface.co/meta-llama/LlamaGuard-7b">LlaMA Gaurd 7B Model</a>, <a href="https://scontent.fblr22-2.fna.fbcdn.net/v/t39.2365-6/408725049_3688557441468029_8103913771964668529_n.pdf?_nc_cat=100&amp;ccb=1-7&amp;_nc_sid=3c67a6&amp;_nc_ohc=FCqeAv0hri0Q7kNvgFYHvpX&amp;_nc_zt=14&amp;_nc_ht=scontent.fblr22-2.fna&amp;_nc_gid=A4MmoE5aSgfdIsB-BvlJ69o&amp;oh=00_AYClX5KL3QrofWqqqtzsC_Th2rnN9cuonSISLwKLZZZZcg&amp;oe=6737E399">paper</a></li>
</ul>


</section>
Expand Down
Loading

0 comments on commit 0fade7c

Please sign in to comment.