-
GenAI – Evaluation Metrics In LLM.
GenAI – LLM Model Evaluation Metrics. Table Of Contents: Automatic Evaluation Metrics. Human Evaluation (Gold Standard). Hallucination Detection. Embedding/Similarity Based. Application-Specific Evaluation. Evaluation Frameworks. (1) Automatic Evaluation Metrics (2) Human Evaluation (Gold Standard). (3) Hallucination Detection (4) Embedding/Similarity Based (5) Application-Specific Evaluation (6) Evaluation Frameworks
-
GenAI – RAG Based Fine Tuning.
-
GenAI – BitFit Tuning.
-
GenAI – Instruction Tuning.
GenAI – Instruction Tuning. Table Of Contents: What Is Instruction Tuning? Steps Involved In Instruction Tuning. Example Of Instruction Tuning. Instruction Tuning Vs Few Shot Prompting. (1) What Is Instruction Tuning ? (2) How Instruction Tuning Helps ? (2) Steps Involved In Instruction Tuning . (2) Example Of Instruction Tuning ? Step-1: Install Required Libraries pip install transformers datasets peft accelerate bitsandbytes Step-2: Sample Instruction Dataset We’ll use a few inline samples. In real cases, use a larger dataset like Alpaca, FLAN, or Self-Instruct. from datasets import Dataset # Sample toy dataset with instruction-style tasks data = [ { "instruction":
-
GenAI – Prompt Tuning .
-
GenAI – Prefix Tuning .
-
GenAI – IA³ Adapters Tuning .
-
GenAI – Bottleneck Adapters Tuning .
-
GenAI – What Is Hugging Face PEFT ?
GenAI – What Is Hugging Face PEFT ? Table Of Contents: What Is Hugging Face PEFT ? What Is PEFT ? Features of Hugging Face PEFT . Example: Using LoRA via Hugging Face PEFT Supported Techniques in PEFT Library (1) What Is Hugging Face PEFT ? (2) What Is PEFT ? (3) Features Of Hugging Face PEFT . (4) Example: Using LoRA via Hugging Face PEFT from transformers import AutoModelForCausalLM, AutoTokenizer from peft import get_peft_model, LoraConfig, TaskType model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf") tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf") # Define LoRA configuration lora_config = LoraConfig( r=8, lora_alpha=16, target_modules=["q_proj", "v_proj"], lora_dropout=0.05, task_type=TaskType.CAUSAL_LM ) # Apply PEFT
-
GenAI – Adapters In LLM.
GenAI – What Is Adapters In LLM ? Table Of Contents: What Is An Adapter ? Why To Use Adapters ? How Adapters Works ? Why Use Adapters ? (1) What Is An Adapter ? (2) Why To Use Adapter ? (3) How Adapter Works ? (4) Why Use Adapters ? (5) List Of Adapters Available ? (6) List Of Adapters Methods Available ? Bottleneck Adapters. Language Adapters – Invertible Adapters. Prefix Tuning. Compacter. LoRA. IA3. Vera. Prompt Tuning. ReFT. (7) Example with Hugging Face’s PEFT (LoRA Adapters) from transformers import AutoModelForCausalLM from peft import get_peft_model, LoraConfig model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
