peft

This repository contains the code to train flan t5 with alpaca instructions and low rank adaptation.

🚀 Engram-PEFT: An unofficial implementation of DeepSeek Engram. Inject high-capacity conditional memory into LLMs via sparse retrieval PEFT without increasing inference FLOPs / DeepSeek Engram 架构的非官方实现。通过参数高效微调 (PEFT) 为大语言模型注入超大规模条件记忆，支持稀疏更新且不增加推理开销。

Preprint: Asymmetry in Low-Rank Adapters of Foundation Models

SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models

Custom model training using modern architectures. 4-bit QLoRA fine-tuning pipeline for LLaMA 3 8B with production-grade optimization. Memory-efficient training on consumer GPUs. Published adapter on HuggingFace. From training pipeline to deployed model.

Train YOLO + VLM with one command. Auto-generate vision-language training data from YOLO labels - no extra labeling needed.

Fine-tune Mistral 7B to generate fashion style suggestions

One GPU. Full LLM workflow. Real benchmarks. No cloud required.

Powerful no-code LLM fine-tuner: upload data → train → deploy in minutes. Unsloth 2-5× acceleration · QLoRA/DPO/RLHF/PPO/ORPO · Reward Model training · GGUF export · vLLM inference · BLEU/ROUGE/BERTScore · full CLI · Heretic Mode to unlock full model potential

Instruction Fine-Tuning of Meta Llama 3.2-3B Instruct on Kannada Conversations. Tailoring the model to follow specific instructions in Kannada, enhancing its ability to generate relevant, context-aware responses based on conversational inputs. Using the Kannada Instruct dataset for fine-tuning! Happy Finetuning 🎋

This hands-on lab walks you through a step-by-step approach to efficiently serving and fine-tuning large-scale Korean models on AWS infrastructure.

Implementation for the different ML tasks on Kaggle platform with GPUs.

A fine-tuning SDK — any open model, any harness, any method. 12 training methods behind one argument; pure-stdlib core.

大模型学习--从模型部署到模型微调，此项目是经过训练营学习后，结合训练营项目，自我理解消化总结，以及创新型应用。可star/fork

LLM-adaptive embeddings (Zero-shot / LoRA) with Generative Topic Modeling & Agent-based workflow for social science text mining

Deferred Continuous Batching in Resource-Efficient Large Language Model Serving (EuroMLSys 2024)

[CVPR 2025 Highlight] Meta LoRA / MetaPEFT: Meta-Learning Hyperparameters for Parameter-Efficient Fine-Tuning (LoRA, Adapter, Prompt Tuning) — Automatic hyperparameter optimization via bi-level meta-learning

Generate multi-speaker conversational datasets for LLM fine-tuning. N-persona support, topic variation, conversation continuation, creative briefs with web search, character pools, Docker support. ShareGPT format with configurable role mapping.

This is AlpaGasus2-QLoRA based on LLaMA2 with AlpaGasus mechanism using QLoRA!

Genie in the Box: Distill Whisper STT => Mistral-7B => Phind/Phind-CodeLlama-34B-v2 => GPT 3.5 => Coqui's TTS/OpenAI TTS