This project is an implementation of the paper: Parameter-Efficient Transfer Learning for NLP, Houlsby [Google], ICML 2019.

End-to-end fine-tuning of Hugging Face models using LoRA, QLoRA, quantization, and PEFT techniques. Optimized for low-memory with efficient model deployment

A LLM(llama) finetuned for work well with mental health assistance

FineTuning LLMs on conversational medical dataset.

Advanced NLP MLOps pipeline for misinformation detection, utilizing RoBERTa with LoRA (PEFT) for efficient fine-tuning. This project focuses on cross-domain generalization across the FakeNews-Kaggle and LIAR datasets, featuring robust data engineering, mixed-precision training, and comprehensive metric evaluation.

Phi-3 Mini: Patient Admission Fine-Tuning

parameter-efficient finetuning method for dynamic faical expression recongition

⭐️⭐️⭐️LLMs RoadMap，帮助各位从transformers仓库视角了解NLP传统任务，模型高效微调，低精度微调，分布式模型训练等工程内容

This is the repo for prompt tuning a language model to improve the given prompt (vague).

This project leverages FLAN-T5 from Hugging Face to perform dialogue summarization, fine-tuning with ROUGE, and detoxifying summaries using PPO and PEFT.

Develop a chatbot that can effectively adapt to context and topic shifts in a conversation, leveraging the Stanford Question Answering Dataset to provide informed and relevant responses, and thereby increasing user satisfaction and engagement.

Implementation of Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning of GPT-2 on the SQuAD dataset for question answering, exploring training efficiency, loss masking, and performance metrics like F1 and Exact Match. Final Course project for Deep Learning at University of Kerman, Spring 2025.

Exploration of Large Language Model (LLM) and its capabilities, specifically dialogue summarization abilities. It highlights the use of a comprehensive fine-tuning approach called Efficient Fine-Tuning (PEFT)

AI Assistant for Customer Support

Lightweight Python toolkit for fine-tuning image datasets with Parameter Efficient Fine Tuning (PEFT) and ViTs

Language Fusion for Parameter-Efficient Cross-lingual Transfer

LoRA + QLoRA fine‑tuning toolkit optimized for Intel Arc Battlemage GPUs

Domain-Specific Sentiment Analysis Model fine-tuned on FinBERT using PEFT (LoRA) to classify financial texts into positive, negative, and neutral sentiment. Achieves high accuracy on domain-specific data with minimal computational cost by leveraging parameter-efficient fine-tuning

KoRA is a novel PEFT method that introduces inter-adapter communication via a CompositionBlock inspired by the Kolmogorov–Arnold Representation Theorem. It composes query, key, and value adapters into a unified representation — achieving robust generalization and cross-domain transfer with minimal parameter overhead.