Tool profile
huggingface/peft
github.com
A library implementing parameter-efficient fine-tuning methods for adapting large pretrained models.
What it does
huggingface/peft
PEFT provides state-of-the-art parameter-efficient fine-tuning methods that adapt large pretrained models by training only a small number of extra parameters, cutting computational and storage costs. It is aimed at machine learning practitioners and researchers working with LLMs and diffusion models, and integrates with Transformers, Diffusers and Accelerate. It is an open-source Python library released under the Apache 2.0 license.
PricingOpen source
RatingN/A
Bookmarks0
Tags
Categories
A concise summary has not been added yet.
FAQ
Frequently asked questions
- What is huggingface/peft?
- PEFT provides state-of-the-art parameter-efficient fine-tuning methods that adapt large pretrained models by training only a small number of extra parameters, cutting computational and storage costs. It is aimed at machine learning practitioners and researchers working with LLMs and diffusion models, and integrates with Transformers, Diffusers and Accelerate. It is an open-source Python library released under the Apache 2.0 license.
- How much does huggingface/peft cost?
- huggingface/peft uses a Open source pricing model. Check the official website for current plans.
- What is huggingface/peft used for?
- huggingface/peft is listed on TolsAI under: Open Source.
- Where can I use huggingface/peft?
- huggingface/peft is available on its official website, github.com.
Explore
More in Open Source
An open-source agentic harness for a self-improving AI agent that plans and executes tasks you describe.
A vectorless, reasoning-based RAG engine that indexes documents as trees and retrieves with LLM reasoning.
A PyTorch-like Python library to build and auto-optimize LLM workflows such as chatbots, RAG and agents.
A modular web UI for generating images, video and audio with AI models like Stable Diffusion, Flux and Wan.
A step-by-step guide to designing AI systems built on LLMs, RAG, and AI agents.
Open-source AI pipeline engine for building, debugging and deploying LLM workflows and agent orchestration from your IDE.
Discussion
Discussion
Log in to join the discussion
No comments yet. Start the discussion.