Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Adapting pretrained models: PEFT/LoRA, instruction tuning, RLHF, DPO and preference alignment.
Signals: fine-tuning, finetuning, lora, peft, qlora, rlhf, dpo, instruction-tuning
281 results
[NeurIPS 2026] Official Repo of "D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models"
NeurIPS 2023, Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
Codes for "CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation"
QLoRA: Efficient Finetuning of Quantized LLMs
No description
1.4B latent diffusion model fine tuning
[ACM Computing Surveys] The collection of awesome papers on alignment of diffusion models.
Automatic1111 WEBUI extension to autofill keyword for custom stable diffusion models and LORA models.
The stable diffusion webui training aid extension helps you quickly and visually train models such as Lora.
This extension replaces the built-in LoRA forward procedure.
Official implementation for "Towards a Unified Self-Distillation Framework for Large Language Models" (https://arxiv.org/abs/2605.06597).
DISC-FinLLM，中文金融大语言模型（LLM），旨在为用户提供金融场景下专业、智能、全面的金融咨询服务。DISC-FinLLM, a Chinese financial large language model (LLM) designed to provide users with professional, intelligent, and comprehensive financial consulting services in financial scenarios.
[TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Finetuning Large Language Models on One Consumer GPU in 2 Bits
Finetuning large language models for GDScript generation.
Best practices for distilling large language models.
Training Large Language Model to Reason in a Continuous Latent Space
BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）
Aligning pretrained language models with instruction data generated by themselves.
Foundations of Medical Large Language Model Learning
Self-Adapting Language Models
[MICCAI 2019 Young Scientist Award] [MedIA Best Paper Award] Models Genesis: self-supervised pre-training for 3D medical images. Learns transferable representations from unlabeled CT and MRI volumes, then fine-tunes for downstream segmentation and classification. Keras and PyTorch weights included.
A Unified Parameter-Efficient Transfer Learning Benchmark for Computer Vision Tasks
SCEPTER is an open-source framework used for training, fine-tuning, and inference with generative models.
24,545 repositories in the index in total.
