# Appendix

* **Practical Seq2Seq** \[Understanding Seq2Seq Models (RNN, LSTM)]
* **Hands on LLMs** \[Understanding LLM from scratch]
* **Running Microsoft Phi‑3 using Hugging Face** -> Practical deployment of Microsoft Phi-3 model locally using Hugging Face APIs
* **Fine‑tune BERT (Sentiment)** -> Hands-on session on fine-tuning BERT to perform sentiment analysis \[From scratch]
* **Flan‑T5 for Classification** -> Prompt formatting, generative vs discriminative
* **Using ChatGPT API for Movie Review Classification** -> Utilize Open AI's ChatGPT API to build a practical sentiment classification pipeline
* T**ext Clustering using Sentence-Transformers** -> Implementing text clustering techniques on ArXiV research papers
* **Topic Modeling with BERTopic** -> Hands-on project applying BERTopic to identify themes from ArXiV research papers
* **LLMs for Text Clustering and Topic Modeling** -> Identification on textual datasets, LLM‑assisted clustering
* **Prompt Engineering** -> Fundamentals and Tips on crafting effective prompts for maximizing LLM outputs with advanced topics such as context learning, Chain-of-Thought, and Tree-of-Thought.
* **LLM** **Guardrails** -> Techniques to set constraints , safety measures
* **LLM** **Quantization** -> Understanding model quantization methods for efficient deployments of LLMs
* **AI** **Agents** (**LangChain**) -> Building complex LLm applications and Agents using LangChain
  * Coding Chains -> Hands on demonstration of creating coding chains using LangChain
  * How to give Memory to LLMs -> Techniques for implementing short-term and long-term memory in LLM applications
  * LLM Agent using LangChain -> Step-by-step project to build a functioning LLM-powered agent
* **Semantic Search & RAG**
  * RAG: Intro & Coding -> Basics of semantic search and RAG concepts
  * LLM Dense Retrieval System -> Build a practical dense retrieval system using LLM embeddings
  * Chunking Strategies for LLM -> Effective strategies for breaking down text into meaningful chunks for retrieval and processing
  * Reranking for Semantic Search -> Understand and implement reranking methods
  * Evaluating Retrieval Systems -> Measure retrieval effectiveness using MAP and nDCG

**Multi Model : Vision Transformers**

* CLIP -> Explore how CLIP bridges vision and language
* BLIP -> Learn how BLIP enhances text generation
* Multimodal LLMs: Text to Image


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://59r.gitbook.io/ml-university/appendix.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.