-
GenAI – What Is QLoRA Fine Tuning ?
GenAI – What Is QLoRA Fine Tuning ? Table Of Contents: What Is Quantization Process ? What Is QLoRA ? Benefits Of QLoRA. Example Of QLoRA. (1) What Is Quantization Process ? (2) What Is QLoRA ? (3) Benefits Of QLoRA ? (4) Example Of QLoRA . transformers peft bitsandbytes datasets from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments, Trainer from peft import prepare_model_for_kbit_training, get_peft_model, LoraConfig, TaskType from datasets import load_dataset from transformers import DataCollatorForLanguageModeling # Load 4-bit quantized model model_name = "meta-llama/Llama-2-7b-hf" model = AutoModelForCausalLM.from_pretrained( model_name, load_in_4bit=True, device_map="auto" ) # Load tokenizer tokenizer = AutoTokenizer.from_pretrained(model_name) # Prepare for QLoRA training model
-
GenAI – What Is LoRA Fine Tuning ?
GenAI – What Is Full LoRA Fine Tuning ? Table Of Contents: What Is LoRA Fine-Tuning? Why Use LoRA? How LoRA Works (Basic Concept) Example Use Case: Fine-Tuning LLaMA-2 7B with LoRA ? When to Use LoRA ? When NOT to Use LoRA ? Summary . (1) What Is Low Rank Adaption (LoRA) Technique ? (2) What Is Happening Inside LoRA ? (3) Why To Use LoRA ? (4) When To Use LoRA ? (5) When Not to Use LoRA ? (6) Example Use Case: Fine-Tuning LLaMA-2 7B with LoRA ? pip install transformers datasets peft accelerate bitsandbytes from transformers
-
GenAI – Full Fine-Tuning LLM Models.
GenAI – What Is Full Fine Tuning LLM Models ? Table Of Contents: What Is Full Fine-Tuning of LLMs? How Full Fine-Tuning Works (Simple Steps) When To Use Full Fine Tuning LLM Models ? Advantages of Full Fine-Tuning Disadvantages of Full Fine-Tuning (1) What Is Full Fine-Tuning LLM Models ? (2) How Full Fine-Tuning Works (Simple Steps) (3) When To Use Full Fine Tuning LLM Models ? (4) Advantages of Full Fine-Tuning (5) Advantages of Full Fine-Tuning
-
GenAI – What Is Fine – Tuning LLM Models ?
GenAI – What Is Fine Tuning LLM Models ? Table Of Contents: What Is Fine-Tuning in LLM Models. Why We Need To Fine Tune LLM Models ? Techniques Available To Fine Tune LLM Models. Comparison Table. Real World Example. Tools & Libraries For Fine Tuning. Summary. (1) What Is Fine Tuning LLM Models ? (2) Why We Need Fine Tuning LLM Models ? (3) Techniques Available To Fine Tune LLM Models. (4) Comparison Table (5) Real-World Example (6) Tools & Libraries for Fine-Tuning (7) Summary
-
GenAI – Types Of Prompting Techniques
GenAI – Types Of Prompting Techniques. Table Of Contents: Zero Short Prompting. Few Short Prompting. Chain Of Thoughts Prompting. Role Prompting. System Prompting. Instruction Tuning. Self Consistency Prompting. (1) Zero Shot Prompting Example – 1 Example – 2 (2) Few Shot Prompting Example – 1 Example – 2 Example – 3 Example – 4 Example – 5 Example – 6 (3) Chain Of Thoughts Prompting Example – 1 Example – 2 Example – 3 Example – 4 Example – 5 How You Will Pass The Questins To The LLM In Chain Of Thoughts ? (4) Role Prompting You are a
-
GenAI – What Is Prompt Engineering ?
GenAI – What Is Prompt Engineering ? Table Of Contents: What is Prompt Engineering? Why is Prompt Engineering Important? Components of a Good Prompt Types of Prompting Techniques How to Write Powerful Prompts (Pro Tips) Real Prompt Examples Advanced Tools That Help with Prompt Engineering In Simple Words Modern Prompt Templates (1) What Is Prompt Engineering ? Example -1 : Text Summarization Example -2 : Email Writing Task Example -3 : Coding Help Example -4 : Customer Support ChatbotCustomer Support Chatbot Example -5 : Content Generation (Social Media Post) (2) Why Prompt Engineering Is Important ? (3) Components Of Good
-
GenAI – Techniques To Train The LLM On Domain Specific Data .
GenAI – Techniques To Train The LLM On Domain Specific Data . Table Of Contents: Prompt Engineering. Instruction Tuning. Retrieval Augmented Generation(RAG) Parameter Efficient Finetuning(PEFT) Full Fine Tuning. Continued Pretraining(DAPT/TAPT). Reinforcement Learning. Knowledge Injection. (1) Prompt Engineering. (2) Instruction Tuning (3) RAG (Retrieval-Augmented Generation) (4) Parameter Efficient Fine-Tuning. (5) Full Fine Tuning (6) Continued Pretraining(DAPT/TAPT). (7) Reinforcement Learning (8) Knowledge Injection
