YanAITalk
YanAITalk
  • Видео 59
  • Просмотров 75 651
Build a PodCast Recommendation with LLM
Audio podcasts have grown to have thousands of episodes and keyword search isn’t very effective at discovering what listeners really are interested in. Creating a concierge that can understand semantically what the listener is interested in will be a vast improvement over search. We’ll describe a software architecture we deployed to several clients that uses pre-trained LLM’s and embedding as a convenient and simple way to bring listeners to content they care about. In this paper we will go through the learnings that lead us to a software architecture for implementing a concierge chatbot for podcast episodes.
Просмотров: 75

Видео

KDD Cup 2024 Multi-task Online Shopping Challenges for LLM: 1st Place Winning Solution46:44KDD Cup 2024 Multi-task Online Shopping Challenges for LLM: 1st Place Winning Solution
KDD Cup 2024 Multi-task Online Shopping Challenges for LLM: 1st Place Winning Solution
Просмотров 7621 день назад
Amazon KDD Cup 2024 1st place winning solution from Nvidia: openreview.net/pdf?id=sv0E1mBhu8
LLM inference optimization: Model Quantization and Distillation45:11LLM inference optimization: Model Quantization and Distillation
LLM inference optimization: Model Quantization and Distillation
Просмотров 409Месяц назад
LLM inference optimization part 2 at Houston Machine Learning meetup
LLM inference optimization: Architecture, KV cache and Flash attention44:06LLM inference optimization: Architecture, KV cache and Flash attention
LLM inference optimization: Architecture, KV cache and Flash attention
Просмотров 1,2 тыс.Месяц назад
LLM inference optimization: Architecture, KV cache and Flash attention
Mixture of Experts: Mixtral 8x7B39:42Mixture of Experts: Mixtral 8x7B
Mixture of Experts: Mixtral 8x7B
Просмотров 1632 месяца назад
Introduce Mistral 7B and Mixtral 8x7B
Scaling Synthetic Data Creation with 1,000,000,000 Personas21:33Scaling Synthetic Data Creation with 1,000,000,000 Personas
Scaling Synthetic Data Creation with 1,000,000,000 Personas
Просмотров 803 месяца назад
Scaling Synthetic Data Creation with 1,000,000,000 Personas
Coding tutorial: LLM fine-tuning with LORA50:58Coding tutorial: LLM fine-tuning with LORA
Coding tutorial: LLM fine-tuning with LORA
Просмотров 3143 месяца назад
colab.research.google.com/drive/1QNOyWzD8H7xA6_ulVeL-5NIXWqMMR7kp
Coding tutorial: RAG with LangChain and Llama328:46Coding tutorial: RAG with LangChain and Llama3
Coding tutorial: RAG with LangChain and Llama3
Просмотров 5204 месяца назад
Build your RAG on free Colab GPU with quantized llama 3! Colab notebook: colab.research.google.com/drive/1CuohoBl31hcAKuRdTYwxGY374v0Mc7uV
Step by Step: Self-Attention Mechanism9:44Step by Step: Self-Attention Mechanism
Step by Step: Self-Attention Mechanism
Просмотров 1075 месяцев назад
Step by step introduction to self-attention mechanism.
LLaMa Family: Alpaca, Vicuna and LLaVA42:56LLaMa Family: Alpaca, Vicuna and LLaVA
LLaMa Family: Alpaca, Vicuna and LLaVA
Просмотров 1745 месяцев назад
Introducing the LLaMA family tree of models: Alpaca, Vicuna and LLaVA
LLaMA 2: Open Foundation and Fine-Tuned Chat Models55:43LLaMA 2: Open Foundation and Fine-Tuned Chat Models
LLaMA 2: Open Foundation and Fine-Tuned Chat Models
Просмотров 3406 месяцев назад
Deep dive into Llama 2 paper: arxiv.org/pdf/2307.09288.pdf
LLM: Textbooks are All You Need19:18LLM: Textbooks are All You Need
LLM: Textbooks are All You Need
Просмотров 1837 месяцев назад
Introduce Phi 1 and Phi 1.5
Boost your Productivity with AI27:41Boost your Productivity with AI
Boost your Productivity with AI
Просмотров 2917 месяцев назад
A working session to see real examples of how we can utilize existing AI tools to boost the productivity for daily study and work: Notion, Codeium, Glasp, Afforai, Magical.
LLaMA: Open and Efficient Foundation Language55:32LLaMA: Open and Efficient Foundation Language
LLaMA: Open and Efficient Foundation Language
Просмотров 3047 месяцев назад
LLM reading group on the LLaMA paper of Open and Efficient Foundation Language: arxiv.org/abs/2302.13971
LLM: Demystify GPT-457:23LLM: Demystify GPT-4
LLM: Demystify GPT-4
Просмотров 5928 месяцев назад
LLM: Demystify GPT-4
LLM: InstructGPT - Follow Instructions with Human Feedback52:30LLM: InstructGPT - Follow Instructions with Human Feedback
LLM: InstructGPT - Follow Instructions with Human Feedback
Просмотров 41010 месяцев назад
LLM: InstructGPT - Follow Instructions with Human Feedback
LLM: GPT-347:18LLM: GPT-3
LLM: GPT-3
Просмотров 16010 месяцев назад
LLM: GPT-3
Scaling Laws for Neural Language Models55:12Scaling Laws for Neural Language Models
Scaling Laws for Neural Language Models
Просмотров 64711 месяцев назад
Scaling Laws for Neural Language Models
LLM: Exploring the Limits of Transfer Learning with a unified Text-to-Text Transformer (T5)50:19LLM: Exploring the Limits of Transfer Learning with a unified Text-to-Text Transformer (T5)
LLM: Exploring the Limits of Transfer Learning with a unified Text-to-Text Transformer (T5)
Просмотров 602Год назад
LLM: Exploring the Limits of Transfer Learning with a unified Text-to-Text Transformer (T5)
Transformer United: Introduction to Vision Transformer (ViT)42:12Transformer United: Introduction to Vision Transformer (ViT)
Transformer United: Introduction to Vision Transformer (ViT)
Просмотров 206Год назад
Transformer United: Introduction to Vision Transformer (ViT)
LLM: Pretraining, Instruction fine-tuning and RLHF1:01:53LLM: Pretraining, Instruction fine-tuning and RLHF
LLM: Pretraining, Instruction fine-tuning and RLHF
Просмотров 6 тыс.Год назад
LLM: Pretraining, Instruction fine-tuning and RLHF
Transformer United: Attention vs 1-D CNN via a Coding Example33:12Transformer United: Attention vs 1-D CNN via a Coding Example
Transformer United: Attention vs 1-D CNN via a Coding Example
Просмотров 203Год назад
Transformer United: Attention vs 1-D CNN via a Coding Example
Transformer United: Introduction to Transformers46:20Transformer United: Introduction to Transformers
Transformer United: Introduction to Transformers
Просмотров 147Год назад
Transformer United: Introduction to Transformers
Transformers in Language: History and Use cases of GPT1:11:15Transformers in Language: History and Use cases of GPT
Transformers in Language: History and Use cases of GPT
Просмотров 300Год назад
Transformers in Language: History and Use cases of GPT
CPU accelerated fine-tuning for image segmentation using PyTorch52:14CPU accelerated fine-tuning for image segmentation using PyTorch
CPU accelerated fine-tuning for image segmentation using PyTorch
Просмотров 575Год назад
CPU accelerated fine-tuning for image segmentation using PyTorch
Explainable Machine Learning56:03Explainable Machine Learning
Explainable Machine Learning
Просмотров 1972 года назад
Explainable Machine Learning
Interpretable Machine Learning59:08Interpretable Machine Learning
Interpretable Machine Learning
Просмотров 6302 года назад
Interpretable Machine Learning
Coding tutorial: Link prediction with Graph Neural Network18:54Coding tutorial: Link prediction with Graph Neural Network
Coding tutorial: Link prediction with Graph Neural Network
Просмотров 4,3 тыс.2 года назад
Coding tutorial: Link prediction with Graph Neural Network
Coding Tutorial: Node Classification with Graph Neural Network31:49Coding Tutorial: Node Classification with Graph Neural Network
Coding Tutorial: Node Classification with Graph Neural Network
Просмотров 2,7 тыс.2 года назад
Coding Tutorial: Node Classification with Graph Neural Network
Machine Learning with Graphs : Knowledge Graph Embeddings1:50:51Machine Learning with Graphs : Knowledge Graph Embeddings
Machine Learning with Graphs : Knowledge Graph Embeddings
Просмотров 6902 года назад
Machine Learning with Graphs : Knowledge Graph Embeddings