peft

CosyVoice3 LoRA fine-tuning companion repo — PEFT integration, 9 known pitfalls from IMDA NSC production runs, corrected from failed full-SFT attempt

High Quality Image Generation Model - Powered with NVIDIA A100

Low-Resource LLM Fine-Tuning using Unsloth and LoRA/QLoRA (WSL2/Linux) 🧠

Fine-tune a local LLM on your own chat history to mimic how you write — an AI doppelganger / digital-twin toolkit built on LLaMA-Factory (LoRA SFT).

Fine tuning Mistral-7b with PEFT(Parameter Efficient Fine-Tuning) and LoRA(Low-Rank Adaptation) on Puffin Dataset(multi-turn conversations between GPT-4 and real humans)

基于Qwen2.5-VL-3B + QLoRA的智能驾驶场景结构化理解系统

[ACMMM'24] MoBA: Mixture of Bi-directional Adapter for Multi-modal Sarcasm Detection

Having fun with ML

Low Tensor Rank adaptation of large language models

Official implementation of the paper "Step-by-Step Unmasking for Parameter-Efficient Fine-tuning of Large Language Models"

7.67× LoRA / 8.35× Full FT speedup for Qwen3.5 (0.8B–27B) on NVIDIA DGX Spark — wall-clock parity with rented H100. Lossless within BF16. Three-command interactive wizard handles model picker, data validator, training, and merge.

Billus 大模型技能库：面向 LLM、VL、多模态与图像生成模型的训练、调参、剪枝、量化与工程化技能库

Companion code for the Manning book 'LLM Customization and Fine-Tuning.' Adapt open-weights LLMs end to end: prompting and RAG, LoRA/QLoRA, full SFT, distillation, and DPO/RLHF alignment.

Advanced LLM fine-tuning techniques: SFT (LoRA, QLoRA, DoRA, P-/Prefix-Tuning), GRPO, DPO, ORPO, KTO & PPO; composable correctness/format rewards + LLM-as-a-Judge evals (DeepEval, Evidently AI) across math, multi-hop, medical & general QA on Llama 3, Mistral, Phi-4, Gemma & Qwen3. Built on TRL, PEFT & Unsloth.