Parameter-Efficient Fine-Tuning using 🤗 PEFT

What changed

Large Language Models (LLMs) based on the transformer architecture, like GPT, T5, and BERT have achieved state-of-the-art results in various Natural Language Processing (NLP) tasks. They have also started foraying into other domains, such as Computer Vision (CV) (VIT, Stable Diffusion, LayoutLM) and Audio (Whisper, XLS-R). Label :", return_tensors="pt") with torch.no_grad(): outputs = model.generate(input_ids=inputs["input_ids"].to("cuda"), max_new_tokens=10) print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0]) # 'complaint' We've released PEFT as an efficient way of tuning large LLMs on downstream tasks and domains, saving a lot of compute and storage while achieving comparable performance to full finetuning.

Why it matters

A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.

How it compares

Related prior coverage to compare against:

• Using LoRA for Efficient Stable Diffusion Fine-Tuning
• Fine-tuning now available for GPT-4o
• Fast LoRA inference for Flux with Diffusers and PEFT

• Using LoRA for Efficient Stable Diffusion Fine-Tuning similarity 0.45
• Fine-tuning now available for GPT-4o similarity 0.27
• Fast LoRA inference for Flux with Diffusers and PEFT similarity 0.26