#peft (7 Repositories)
Ranked open-source repositories tagged with #peft, scored by pull request acceptance likelihood and maintainer engagement velocity.
35.5%
64.1h
7 repositories tagged #peft
ModelCloud/GPTQModel
LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
MakazhanAlpamys/Soup
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
hiyouga/LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
wxhcore/bumblecore
An LLM training framework built from the ground up, featuring a custom BumbleBee architecture and end-to-end support for multiple open-source models across Pretraining → SFT → RLHF/DPO.
ashishpatel26/LLM-Finetuning
LLM Finetuning with peft
DaoyuanLi2816/can-i-finetune-this
Estimate whether a Hugging Face model fits and fine-tunes on your local GPU.