​Python programs

​

1. Introduction to Natural Language Processing
2. NLP concepts- Tokenization, Stemming and Lemmatization, NER, Sentiment Analysis, Word Embedding, Bag of Words, Vector Embedding
3. Introduction to AI
4. Introduction to Machine Learning
5. Machine Learning Algorithms,
6. Supervised Learning, Unsupervised Learning,Deep Learning and Reinforcement Algorithm.
7. Industry Use cases of Machine Learning
8. Regression Algorithms
9. Predictions, errors, accuracy
10. Gradient Descent & Convergence of Learning Algorithm
11. Learning Function, Learning Rate, Accuracy

Text Summarization

​

1. Introduction to Deep Learning
2. Deep Learning Introduction, TensorFlow ,  Keras Basics, Artificial Neural Networks(ANN) Basics, Back Propagation, Weights & Biases, Loss Functions & Optimizers in Feedforward Neural Networks
3. Introduction to Convolutional Neural Networks
4. Introduction to Recurrent Neural Network
   

Image Classification​

​

1. Introduction to Transformers
2. Why Generative AI
3. Generative AI: The future of development
4. Introduction to LLM, LLM Models
5. Prompting the LLM like a chatbot
6. Prompt Engineering a General Overview
7. Prompt Techniques
8. LLM Opensource Models
9. Industry practices , infrastructure and tools related to LLM stack
10. Open Source Base Models

• ChatGPT/GPT-3.5/4
• LlaMA
• Cohere
• Hugging face

Working with different prompts

​

1. Langchain Framework
2. Introduction
3. Functions, Tools and Agents with Langchain
4. Understanding Context Window, Character Splitter, Recursive Character Splitter, Semantic Splitter
5. Retrieval Augmented Generation(RAG)
6. Augment your LLM with RAG
7. Sentence Window Retrieval
8. Vector Embedding
9. Vector Stores
10. RAG with Langchain

Creating RAG system, Use your own data with LLM.

​

1. Advanced RAG – query, indexing , nlp to database --Multi document RAG
2. When to apply RAG and
3. RAG as agent tool
4. Chatbot

Advanced RAG

1. Need for FineTuning LLMs
2. Standard and Instructional fine tuning
3. Parameter Efficient Fine Tuning(PEFT)
4. Low Rank Adapters(LORA)

Fine tuning LLM model with PEFT and LORA​

​

1. Introduction to AWS Bedrock
2. Amazon Bedrock Playgrounds
3. Base Foundation Model
4. Custom Models,
5. Training jobs, Model Evaluation

​Working with Amazon Bedrock​