AI Briefing#peft
The latest AI and developer news about #peft, with the original source and a short summary.
The latest AI and developer news about #peft, with the original source and a short summary.
Ramp Labs has open-sourced PorTAL, a framework that supports cross-model LoRA adaptation.
A public leaderboard has launched to compete on LoRA fine-tuning speed under identical hardware and dataset conditions.
This piece examines the methodologies for evaluating LLM faithfulness and the latest research trends for improving efficiency, as discussed at ACL 2024.
We propose the K-Merge framework, which continually expands an LLM's capabilities without data even in storage-constrained on-device environments.
MiCA, which improves training efficiency by leveraging the minor singular subspace of weight matrices, has been integrated into the PEFT library.
Despite LoRA's high market share, a variety of PEFT techniques should be considered to improve performance.
The KappaTune fine-tuning technique has been officially integrated into Hugging Face's PEFT library.
This summarizes the major technical issues and solutions that arise during fine-tuning and deployment of the Gemma-4 model.
FuriosaAI presented 6 research papers at ICML and ACL that enhance model efficiency, reasoning capability, and flexibility.
A method using Diffusers and PEFT was released that improves LoRA inference speed for Flux models by about 2.3x.
OpenAI is improving fine-tuning API features and expanding support for custom models through its custom models program.
Hugging Face has released a guide on using PEFT and QLoRA to efficiently fine-tune Gemma models.
Hugging Face's PEFT library now supports new merging methods that can efficiently combine LoRA adapters.
A guide summarizing Hugging Face's open source LLM models, licenses, serving tools, and PEFT techniques.
Hugging Face has integrated TRL and PEFT to enable RLHF training of 20B-scale LLMs even on consumer GPUs.
The 🤗 PEFT library, which enables fine-tuning of large models with fewer resources, has been released.