Optimizing LLM Fine-Tuning with PEFT and LoRA Adapter-Tuning for GPU Performance

Optimizing LLM Fine-Tuning with PEFT and LoRA Adapter-Tuning for GPU Performance

Discover AI via YouTube Direct link

bfloat16 and XLA compiler PyTorch 2.0

10 of 15

10 of 15

bfloat16 and XLA compiler PyTorch 2.0

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Optimizing LLM Fine-Tuning with PEFT and LoRA Adapter-Tuning for GPU Performance

Automatically move to the next video in the Classroom when playback concludes

  1. 1 PEFT source code LoRA, pre-fix tuning,..
  2. 2 Llama - LoRA fine-tuning code
  3. 3 Create PEFT - LoRA Model Seq2Seq
  4. 4 Trainable parameters of PEFT - LoRA model
  5. 5 get_peft_model
  6. 6 PEFT - LoRA - 8bit model of OPT 6.7B LLM
  7. 7 load_in_8bit
  8. 8 INT8 Quantization explained
  9. 9 Fine-tune a quantized model
  10. 10 bfloat16 and XLA compiler PyTorch 2.0
  11. 11 Freeze all pre-trained layer weight tensors
  12. 12 Adapter-tuning of PEFT - LoRA model
  13. 13 Save tuned PEFT - LoRA Adapter weights
  14. 14 Run inference of new PEFT - LoRA adapter - tuned LLM
  15. 15 Load your Adapter-tuned PEFT - LoRA model

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.