Large Language Models Process Explained. What Makes Them Tick and How They Work Under the Hood!
AemonAlgiz
Large Language Models Process Explained. What Makes Them Tick and How They Work Under the Hood!
21:54
SuperHOT, 8k and 16k Local Token Context! How Does It Work? What We Believed About LLM’s Was Wrong.
AemonAlgiz
SuperHOT, 8k and 16k Local Token Context! How Does It Work? What We Believed About LLM’s Was Wrong.
12:23
Reinforcement Learning From Human Feedback, RLHF. Overview of the Process. Strengths and Weaknesses.
AemonAlgiz
Reinforcement Learning From Human Feedback, RLHF. Overview of the Process. Strengths and Weaknesses.
18:44
Landmark Attention Training Walkthrough! QLoRA for Faster, Better, and Even Local Training.
AemonAlgiz
Landmark Attention Training Walkthrough! QLoRA for Faster, Better, and Even Local Training.
9:48
Why Do LLM’s Have Context Limits? How Can We Increase the Context? ALiBi and Landmark Attention!
AemonAlgiz
Why Do LLM’s Have Context Limits? How Can We Increase the Context? ALiBi and Landmark Attention!
19:49
SpQR - Sparse Quantization Representation - Live Stream #4
AemonAlgiz
SpQR - Sparse Quantization Representation - Live Stream #4
56:29
How To Create Datasets for Finetuning From Multiple Sources! Improving Finetunes With Embeddings.
AemonAlgiz
How To Create Datasets for Finetuning From Multiple Sources! Improving Finetunes With Embeddings.
17:22
Finetuning, Embeddings, QLoRA/LoRA, and More! Livestream Q&A Session #3
AemonAlgiz
Finetuning, Embeddings, QLoRA/LoRA, and More! Livestream Q&A Session #3
1:27:27
QLoRA PEFT Walkthrough! Hyperparameters Explained, Dataset Requirements, and Comparing Repo's.
AemonAlgiz
QLoRA PEFT Walkthrough! Hyperparameters Explained, Dataset Requirements, and Comparing Repo's.
14:55
QLoRA Is More Than Memory Optimization. Train Your Models With 10% of the Data for More Performance.
AemonAlgiz
QLoRA Is More Than Memory Optimization. Train Your Models With 10% of the Data for More Performance.
14:48
LoRA Q&A with Oobabooga! Embeddings or Finetuning?
AemonAlgiz
LoRA Q&A with Oobabooga! Embeddings or Finetuning?
59:24
PEFT LoRA Finetuning With Oobabooga! How To Configure Other Models Than Alpaca/LLaMA Step-By-Step.
AemonAlgiz
PEFT LoRA Finetuning With Oobabooga! How To Configure Other Models Than Alpaca/LLaMA Step-By-Step.
10:23
What Is Positional Encoding? How To Use Word and Sentence Embeddings with BERT and Instructor-XL!
AemonAlgiz
What Is Positional Encoding? How To Use Word and Sentence Embeddings with BERT and Instructor-XL!
14:08
LLaMa GPTQ 4-Bit Quantization. Billions of Parameters Made Smaller and Smarter. How Does it Work?
AemonAlgiz
LLaMa GPTQ 4-Bit Quantization. Billions of Parameters Made Smaller and Smarter. How Does it Work?
11:03
Fine-Tune Language Models with LoRA! OobaBooga Walkthrough and Explanation.
AemonAlgiz
Fine-Tune Language Models with LoRA! OobaBooga Walkthrough and Explanation.
9:21
Google's Concern Over No Moat Against Open Source LLMs: The Breakthrough Technologies Behind It.
AemonAlgiz
Google's Concern Over No Moat Against Open Source LLMs: The Breakthrough Technologies Behind It.
6:49
What is Tokenization in Transformers and How Are They Made? Byte Pair Encoding Explained Simply.
AemonAlgiz
What is Tokenization in Transformers and How Are They Made? Byte Pair Encoding Explained Simply.
3:32
I Got API Access to GPT4! A Ton of Options to Choose From, Is There Anything You Would Like to See?
AemonAlgiz
I Got API Access to GPT4! A Ton of Options to Choose From, Is There Anything You Would Like to See?
0:46
Bing AI Open to the Public! What Features Are Available and What About Plugins? Here’s What We Know!
AemonAlgiz
Bing AI Open to the Public! What Features Are Available and What About Plugins? Here’s What We Know!
0:52
Geoffrey Hinton's Strong Beliefs, OpenAI to Meet With Congress, IBM To Not Hire 7800. What a week.
AemonAlgiz
Geoffrey Hinton's Strong Beliefs, OpenAI to Meet With Congress, IBM To Not Hire 7800. What a week.
0:52
Geoffrey Hinton, Google's VP of Engineering and Godfather of AI, Leaves? What Are His Fears About?
AemonAlgiz
Geoffrey Hinton, Google's VP of Engineering and Godfather of AI, Leaves? What Are His Fears About?
0:51
AI To Detect and Cure Cancers? How AI Can Help Medical Professionals Make Better Decisions!
AemonAlgiz
AI To Detect and Cure Cancers? How AI Can Help Medical Professionals Make Better Decisions!
0:54
Embeddings in Machine Learning! What Are They and How Do We Use Them? How We Can Teach Computers.
AemonAlgiz
Embeddings in Machine Learning! What Are They and How Do We Use Them? How We Can Teach Computers.
8:43
Updated Installation for Oobabooga Vicuna 13B And GGML! 4-Bit Quantization, CPU Near As Fast As GPU.
AemonAlgiz
Updated Installation for Oobabooga Vicuna 13B And GGML! 4-Bit Quantization, CPU Near As Fast As GPU.
4:34
Why Search Your Data When You Can Ask It? Vector Databases and Embeddings to Level Up Your Corpus.
AemonAlgiz
Why Search Your Data When You Can Ask It? Vector Databases and Embeddings to Level Up Your Corpus.
4:27
Update on Alice the Scambait Bot. She Needs a Voice. Does Anyone Know a Good Text To Speech Library?
AemonAlgiz
Update on Alice the Scambait Bot. She Needs a Voice. Does Anyone Know a Good Text To Speech Library?
0:43
Scambait with ChatGPT/LLM’s? In Honor of Kitboga’s TTS AI. Alice Seems Like a Good Name.
AemonAlgiz
Scambait with ChatGPT/LLM’s? In Honor of Kitboga’s TTS AI. Alice Seems Like a Good Name.
0:42
ChatGPT Plays the Sims? Smallville GPT, More Human than Human, Except When it Emulates our Pets.
AemonAlgiz
ChatGPT Plays the Sims? Smallville GPT, More Human than Human, Except When it Emulates our Pets.
0:48
Vicuna 13B V1.1! With 4-Bit Quantization, What Can't it Run On? OobaBooga One Click Installer.
AemonAlgiz
Vicuna 13B V1.1! With 4-Bit Quantization, What Can't it Run On? OobaBooga One Click Installer.
5:08
Responding to Luke at Linus Tech Tips. Will Companies Move to On-Prem solutions for ChatGPT? Maybe.
AemonAlgiz
Responding to Luke at Linus Tech Tips. Will Companies Move to On-Prem solutions for ChatGPT? Maybe.
0:56
ChatGPT Sure is Stable Today! Conversation Not Found You Say.
AemonAlgiz
ChatGPT Sure is Stable Today! Conversation Not Found You Say.
0:31
GPT-5 is How Soon? What do We Know? Will it Reach Artificial General Intelligence or Beyond?
AemonAlgiz
GPT-5 is How Soon? What do We Know? Will it Reach Artificial General Intelligence or Beyond?
0:56
Microsoft Jarvis, Bringing ChatGPT Closer to Artificial General Intelligence and Autonomy!
AemonAlgiz
Microsoft Jarvis, Bringing ChatGPT Closer to Artificial General Intelligence and Autonomy!
1:00
Save Money On Your GPT Application? Cost Savings To Make Your Application Go To The Moon!
AemonAlgiz
Save Money On Your GPT Application? Cost Savings To Make Your Application Go To The Moon!
0:58
Do AI's Dream? How We Can Understand Neural Networks And Improve Their Performance!
AemonAlgiz
Do AI's Dream? How We Can Understand Neural Networks And Improve Their Performance!
0:58
My dogs also demand the cheese tax. #cheesetax
AemonAlgiz
My dogs also demand the cheese tax. #cheesetax
0:22
Are We At Artificial General Intelligence? AutoGPT and BabyAGI, How To Automate Your Life, Today!
AemonAlgiz
Are We At Artificial General Intelligence? AutoGPT and BabyAGI, How To Automate Your Life, Today!
1:00
FastChat Vicuna Can Support What!? A Complete Walkthrough. Will you use ChatGPT again?
AemonAlgiz
FastChat Vicuna Can Support What!? A Complete Walkthrough. Will you use ChatGPT again?
6:56
60 Seconds of How You Can Teach AI To Read Part 2 Byte Pair Encoding
AemonAlgiz
60 Seconds of How You Can Teach AI To Read Part 2 Byte Pair Encoding
0:58
ChatGPT Killer On Your Computer? Let's Install FastChat Alpaca Vicuna!
AemonAlgiz
ChatGPT Killer On Your Computer? Let's Install FastChat Alpaca Vicuna!
6:13
60 Seconds of CUDA Can be Painful GPT, Vicuna
AemonAlgiz
60 Seconds of CUDA Can be Painful GPT, Vicuna
0:57
60 Seconds of Run GPT 4 On Your Computer? Stanford's Open Source Vicuna Is Here!
AemonAlgiz
60 Seconds of Run GPT 4 On Your Computer? Stanford's Open Source Vicuna Is Here!
0:54
Hugging GPT - Automate Your Life, With GPT and Hugging Face!
AemonAlgiz
Hugging GPT - Automate Your Life, With GPT and Hugging Face!
5:34
60 Seconds of a Ramble On Glitch Tokens
AemonAlgiz
60 Seconds of a Ramble On Glitch Tokens
0:56
60 Seconds of How You Can Teach AI To Read Part 1
AemonAlgiz
60 Seconds of How You Can Teach AI To Read Part 1
0:58
60 Seconds of Could AI Scam You?
AemonAlgiz
60 Seconds of Could AI Scam You?
0:57
60 Seconds of Twitter's Open Source
AemonAlgiz
60 Seconds of Twitter's Open Source
0:57
60 Seconds of The Potential Dangers of AI. We Must Hold Ourselves Accountable.
AemonAlgiz
60 Seconds of The Potential Dangers of AI. We Must Hold Ourselves Accountable.
0:59
60 Seconds of Unleashing Your Creativity with Midjourney
AemonAlgiz
60 Seconds of Unleashing Your Creativity with Midjourney
0:57
60 Seconds of Midjourney and AI Art
AemonAlgiz
60 Seconds of Midjourney and AI Art
0:58
60 Seconds of AI Hallucinations Explained
AemonAlgiz
60 Seconds of AI Hallucinations Explained
0:57
60 Seconds of Training Your Own GPT Model.
AemonAlgiz
60 Seconds of Training Your Own GPT Model.
0:58
Fine tune ChatGPT. Leverage Your Data to Enhance Search and Improve Your Chat Experience.
AemonAlgiz
Fine tune ChatGPT. Leverage Your Data to Enhance Search and Improve Your Chat Experience.
4:17
60 Seconds of ChatGPT Parameters
AemonAlgiz
60 Seconds of ChatGPT Parameters
0:57
Alan Turing, A Brief History #shorts
AemonAlgiz
Alan Turing, A Brief History #shorts
0:58