Popular GitHub Repositories for Finetuning Llms

Mastering Applied AI, One Concept at a Time

Auto Data is a library designed for quick and effortless creation of datasets tailored for fine-tuning Large Language Models (LLMs).

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

On Memorization of Large Language Models in Logical Reasoning

A Gradio web UI for Large Language Models. Supports LoRA/QLoRA finetuning,RAG(Retrieval-augmented generation) and Chat

Fine-tune Mistral 7B to generate fashion style suggestions

Official repository of my book "A Hands-On Guide to Fine-Tuning LLMs with PyTorch and Hugging Face"

[NeurIPS 2023] Make Your Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning

Medical Language Model fine-tuned using pretraining, instruction tuning, and Direct Preference Optimization (DPO). Progresses from general medical knowledge to specific instruction following, with experiments in preference alignment for improved medical text generation and understanding.

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

SEIKO is a novel reinforcement learning method to efficiently fine-tune diffusion models in an online setting. Our methods outperform all baselines (PPO, classifier-based guidance, direct reward backpropagation) for fine-tuning Stable Diffusion.

A open-source framework designed to adapt pre-trained Language Models (LLMs), such as Llama, Mistral, and Mixtral, to a wide array of domains and languages.

[EMNLP 2024] Quantize LLM to extremely low-bit, and finetune the quantized LLMs

Finetuning Google's Gemma Model for Translating Natural Language into SQL

qwen-1.5-1.8B sentiment analysis with prompt optimization and qlora fine-tuning

A curated list of Parameter Efficient Fine-tuning papers with a TL;DR

Code for fine-tuning Llama2 LLM with custom text dataset to produce film character styled responses

Prompt engineering with Langchain and fine-tuning the CodeLlama model. The main aim is to generate task-specific C++ code snippets. Experiment with various prompts and models to create accurate C++ code. Unit test is conducted to validate the correctness and effectiveness of the generated code snippets.

ResurrectAI is an AI-driven chat application designed to bring the wisdom and knowledge of great historical personalities to life. Leveraging advanced language models and fine-tuning techniques, ResurrectAI enables users to interact with AI avatars of iconic figures, gaining access to their insights, guidance, and philosophical teaching in realtime

A c++ framework on efficient training & fine-tuning LLMs