fine-tuning

This comprehensive guide provides a universal process for preparing your own speech datasets and training a custom Text-to-Speech (TTS) model.

Predict the Body Mass Index with one image of a human face, with state-of-the-art results.

Simple and lightweight tool to fine-tune GPT models (like GPT-2 and GPT-Neo) using your own data — built with Python and Transformers. Adapt powerful language models to your domain with ease.

Personal Identifiable Information (PII) entity detection and performance enhancement with synthetic data generation

A family of highly efficient, lightweight yet powerful optimizers.

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

This repository exploits a finely tuned Stable Diffusion model and the robust DreamBooth framework to generate distinctive and personalizable avatars.

[TACL, EMNLP 2025 Oral] Code, datasets, and checkpoints for the paper "CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation"

Fine-tuning Large Language Models (LLMs) for Text Classification Task

Flood detection from images using deep learning. Deep learning library KERAS was employed and MobileNet architecture was fine-tuned for image classification task.

无需预算，使用你的个人数据克隆自己——赛博飞升！Clone yourself by tuning a LLM using your own data.

疫情期间网民情绪识别比赛baseline，使用BERT进行端到端的fine-tuning，datafountain平台，平台评测F1值0.716。

Training pipeline for fine tuning Phi-3-mini-instruct to follow the Socratic method

Resume Insight: Fine-Tuning LLM for Resume Analysis

Multi-domain Recommendation with Adapter Tuning

Fine-tuned Qwen2-VL-7B for LaTeX OCR using LoRA and Unsloth on the LaTeX OCR dataset. Built augmentation pipeline (rotation, noise, contrast jitter), ran LoRA rank sweep (r=8/16/32), and evaluated across CER, Token F1, BLEU-4, and Exact Match. Deployed as a Gradio Space with live metric computation.

A highly memory-efficient fine-tuning toolkit for SDXL and ANIMA, combining modern VRAM-saving techniques with custom optimizers to enable full-quality model training on GPUs with as little as 12 GB of VRAM.

Enterprise-grade Knowledge Distillation framework for Persian Mental Health analysis. Distills reasoning capabilities from Llama-3-70b into a local Gemma-3-1b model using QLoRA and synthetic Chain-of-Thought datasets.

Code for "BayesAdapter: Being Bayesian, Inexpensively and Robustly, via Bayeisan Fine-tuning"

PipelineLLM 是一个系统性的大语言模型（LLM）后训练学习项目，涵盖从监督微调（SFT）到偏好优化（DPO）、强化学习（RLHF/PPO/GRPO）再到持续学习（Continual Learning)的完整技术栈。