The Power of Local AI
37 min

The Power of Local AI

MLOps World - MLOps World & Generative AI World 2024
Christian Crowley
local-ai private-ai open-source-models personalization sanctum-ai artificial-intelligence large-language-models llm privacy security hugging-face data-privacy
The Who, What, and Why of Data Lake Table Formats
48 min

The Who, What, and Why of Data Lake Table Formats

MLOps World - MLOps World & Generative AI World 2024
Alex Merced
data-lakehouse table-formats apache-hudi delta-lake data-partitioning z-order-sorting schema-evolution data-lake apache-iceberg data-management data-engineering metadata
Efficiently Fine-Tune And Serve Your Own LLMs
42 min

Efficiently Fine-Tune And Serve Your Own LLMs

MLOps World - MLOps World & Generative AI World 2024
Alex Sherstinsky
llm-fine-tuning predibase ludwig lorax large-language-models lora parameter-efficient-fine-tuning peft transformer-models mistral-7b model-serving inference
Building ML and GenAI Systems with Metaflow
48 min

Building ML and GenAI Systems with Metaflow

MLOps World - MLOps World & Generative AI World 2024
Ville Tuulos
ai-systems ml machine-learning genai generative-ai metaflow data-engineering model-training inference python mlops
Data Versioning in Generative AI: A Pathway to Cost-effective ML
36 min

Data Versioning in Generative AI: A Pathway to Cost-effective ML

MLOps World - MLOps World & Generative AI World 2024
Dmitry Petrov
dataset-sharing annotations generative-ai ml data-versioning machine-learning dvc cost-optimization collaboration embeddings
Enhance Cost Efficiency in Domain Adaptation with PruneMe
17 min

Enhance Cost Efficiency in Domain Adaptation with PruneMe

MLOps World - MLOps World & Generative AI World 2024
Shamane Siri
domain-adaptation continual-pretraining ai-research llm large-language-models pruning cost-efficiency model-optimization transformer nlp
Better Chatbots with Advanced RAG Techniques
50 min

Better Chatbots with Advanced RAG Techniques

MLOps World - MLOps World & Generative AI World 2024
Zain Hasan
vector-databases weaviate chatbots hybrid-search query-generation semantic-search rag retrieval-augmented-generation llms language-models machine-learning ai
Empowering Data Science Teams: Harnessing AI with Appen
31 min

Empowering Data Science Teams: Harnessing AI with Appen

MLOps World - MLOps World & Generative AI World 2024
Sasha McGrath Geoffrey LaPorte
training-data ai data-science machine-learning llm generative-ai data-annotation data-quality collaboration model-building
Evaluating LLMs and RAG Pipelines at Scale
36 min

Evaluating LLMs and RAG Pipelines at Scale

MLOps World - MLOps World & Generative AI World 2024
Eric Korman
valor llm rag mlops llm-ops pipelines language-models natural-language-processing data-management model-training model-deployment
Finding training inefficiencies with CentML DeepView
41 min

Finding training inefficiencies with CentML DeepView

MLOps World - MLOps World & Generative AI World 2024
Yubo Gao
visual-profiler training-throughput batch-size mixed-precision tensor-cores flash-attention deep-learning machine-learning performance-optimization profiling gpu-utilization pytorch tensorflow model-deployment cost-optimization energy-efficiency
Function Calling for LLMs: RAG without a Vector Database
40 min

Function Calling for LLMs: RAG without a Vector Database

MLOps World - MLOps World & Generative AI World 2024
Jim Dowling
feature-store llm rag function-calling vector-database ai data-modeling natural-language-processing retrieval-augmented-generation api machine-learning
LLM Fine-Tuning for Modern AI Teams: How One E-Commerce Unicorn Cut Inference Cost by 90%
47 min

LLM Fine-Tuning for Modern AI Teams: How One E-Commerce Unicorn Cut Inference Cost by 90%

MLOps World - MLOps World & Generative AI World 2024
Emmanuel Turlay
inference-cost data-preparation mistral-7b gpt-3.5 cost-reduction llm fine-tuning ai machine-learning e-commerce natural-language-processing model-evaluation