Three Ways to Evaluate LLMs

Alfred: An Open-Source Tool for Building Training Data with Foundation Models and Weak Supervision

Transforming Call Center Operations with Snorkel AI

How to Add/Remove/Manage Foundation Models (FMs) and Large Language Models (LLMs) in Snorkel Flow

How to Create Computer Vision Applications in Snorkel Flow

How to Upload Images and PDFs into Snorkel Flow

How to Optimize RAG Pipelines for Domain- and Enterprise-Specific Tasks

Three Ways to Evaluate LLMs

The Iterative LLM Development Loop in Snorkel Flow

How to activate Llama 3.1 405B in Snorkel Flow

LLM Evaluation for Production Enterprise Applications

DEMO: How to Evaluate Enterprise LLMs in Snorkel Flow

How to Evaluate LLM Performance for Domain-Specific Use Cases

LLM Distillation: How Step-by-Step LLM Distillation Yields Incredible Results #shorts

Build Better LLMs Through Data Slicing

When, Why and How to Fine-Tune LLMs for Enterprise Applications

DEMO: How To Align LLMs for Enterprise Applications in Snorkel Flow

4 Ways to Align LLMs: RLHF, DPO, KTO, and ORPO

LLM Application Improvements: The View That Developers Need

Building Better LLM Applications in Snorkel Flow: An Overview #shorts

We Need Thousands of Research Papers to Flesh Out Data-Centric AI, Andrew Ng #shorts

How New Research Extends Weak Supervision Beyond Classification Problems

The LLM application iteration loop within Snorkel Flow #shorts

Why You Should Never Fully Trust a Reward Model #shorts

How to Fine-Tune LLMs to Perform Specialized Tasks Accurately