🧰 peft

The items that name it 8

• Welcome Le Chonk: Mistral Large 4 on Hugging Face
  article2026-10-29

  Library providing LoRA configuration for fine-tuning Mistral Large 4.

• Amazon’s Trainium Takes a Strike at the Training King
  article2026-10-23

  Part of the PyTorch ecosystem named among libraries.

• TorchNeuron: running HF models on AWS Trainium is easier than ever
  article2026-10-19

  Hugging Face parameter-efficient fine-tuning library that runs on Trainium.

• Welcome Beam: a 501B open model you can own, customize, and scale
  article2026-10-16

  LoRA adapters to keep memory manageable when fine-tuning

• Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta
  article2026-10-15It is written here as PEFT (LoraConfig).

  LoRA adapters on attention projections.

• Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL
  writeup2026-09-10It is written here as PEFT (LoraConfig).

  Python library used to configure the LoRA adapter (rank, alpha, target modules) passed to AsyncGRPOTrainer

• whitecircle/halo
  repo2026-08-26

  Hugging Face library providing LoRA/QLoRA adapters used by Halo.

• MakazhanAlpamys/Soup
  repo2026-08-14

  Library providing LoRA/PEFT support used by Soup's training stack