Topic mix

Fine-tuning

21 moments from 18 videos · 58:07 min total

Learn how to adapt large models to custom domains. This playlist highlights technical segments focusing on dataset preparation, LoRA, and efficient optimization strategies.

Cutting LLM Costs Without Cutting Quality: How to Beat Proprietary LLMs with Fine-Tuned Open Source
Play section Identifying when narrow tasks require custom model fine-tuning Identifying when narrow tasks require custom model fine-tuning thumbnail Identifying when narrow tasks require custom model fine-tuning Determining when to transition from prompt engineering and retrieval-augmented generation to supervised fine-tuning reduces latency and API dependency.
Play section Trade-offs between proprietary, open weight, and fine-tuned models Trade-offs between proprietary, open weight, and fine-tuned models thumbnail Trade-offs between proprietary, open weight, and fine-tuned models Navigating model selection requires balancing organizational control, hosting responsibilities, and specific task complexities.
Fine-Tuning Small Language Models for Agentic AI
Play section Methods for supervised fine-tuning and reinforcement learning Methods for supervised fine-tuning and reinforcement learning thumbnail Methods for supervised fine-tuning and reinforcement learning Data distillation enables supervised fine-tuning while GRPO offers reinforcement learning with verifiable rewards.
Play section Benchmark limitations and final recommendations for fine-tuning models Benchmark limitations and final recommendations for fine-tuning models thumbnail Benchmark limitations and final recommendations for fine-tuning models Despite evaluation limits, supervised fine-tuning offers clear return on investment for highly specialized sub-agent tasks.
Play section Implementing simple supervised fine-tuning with the Unsloth library Implementing simple supervised fine-tuning with the Unsloth library thumbnail Implementing simple supervised fine-tuning with the Unsloth library Specific training prompts and the Unsloth library streamline the process of fine-tuning quantized models.
Point. Ask. Answer. Building Vision into AI on Constrained Hardware
Play section Fine-tuning open models for specific reasoning tasks Fine-tuning open models for specific reasoning tasks thumbnail Fine-tuning open models for specific reasoning tasks Improving task-specific reasoning without the cost of full training by fine-tuning quantized open-source models.

Loading the rest of your playlist…

Your mix. Instantly.

More mixes