peft

Finetuning of Falcon-7B LLM using QLoRA on Mental Health Conversational Dataset

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.

Collection of Tools and Papers related to Adapters / Parameter-Efficient Transfer Learning/ Fine-Tuning

Stable and Efficient Reinforcement Learning for Trillion-Parameter LLMs

[ICML2025] Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment

Speedrunning LoRA fine-tuning: frozen task, frozen hardware, public wall-clock leaderboard. modded-nanogpt for fine-tuning.

An Integrated Library for Tuning, Deploying and Interpreting Genomic Models

This is the official repository for the paper "Flora: Low-Rank Adapters Are Secretly Gradient Compressors" in ICML 2024.

[ICLR 2024] This is the repository for the paper titled "DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning"

Fine-Tuning Dataset Auto-Generation for Graph Query Languages.

An LLM training framework built from the ground up, featuring a custom BumbleBee architecture and end-to-end support for multiple open-source models across Pretraining → SFT → RLHF/DPO.

Fine-Tuning Falcon-7B, LLAMA 2 with QLoRA to create an advanced AI model with a profound understanding of the Indian legal context.

🚀 Easy, open-source LLM finetuning with one-line commands, seamless cloud integration, and popular optimization frameworks. ✨

MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Transformers — with support for 300+ large language models (Qwen3-Next, GLM-5.2, Deepseek-V4, MiniMax-2.7, ...) and 200+ multimodal large models (Qwen3.5, Qwen3-Omni, Gemma4, ...).

Finetune mistral-7b-instruct for sentence embeddings

PyTorch Reimplementation of LoRA (featuring with supporting nn.MultiheadAttention in OpenCLIP)

Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract + two-phase Train→Nudge (silver-medal NVIDIA Nemotron reasoning recipe, as a tested library).

Code for NOLA, an implementation of "nola: Compressing LoRA using Linear Combination of Random Basis"

Efficient Multimodal Foundation Model Adaptation for Recommendation

CompanionLLM - A framework to finetune LLMs to be your own sentient conversational companion