finetune-llm

FineTune LLMs in few lines of code (Text2Text, Text2Speech, Speech2Text)

Fine-tuning Qwen2.5-VL for vision-language tasks | Optimized for Vision understanding | LoRA & PEFT support.

Gen AI Large Language Model Projects

Querypls🛠️: WebApp that Simplify SQL with Your Prompts. Transforming questions into SQL commands effortlessly.

从对话数据到训练:数字分身 + 模型蒸馏 From Dialogue Data to Training Closed-Loop: Digital Twin + Model Distillation

使用LLaMA-Factory微调多模态大语言模型的示例代码 Demo of Finetuning Multimodal LLM with LLaMA-Factory

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.

🎯 Generate fake data for finetune of AI, Just like a person.

A curated collection of interview questions and expert answers focused on Large Language Models (LLMs). Whether you're preparing for a Data Scientist, ML Engineer, or AI Researcher role, this repository is designed to help you crack interviews confidently in the rapidly evolving world of Generative AI.

这是一个很可爱的色妹妹，送给每一个需要的人~

LLM, Fine Tuning, Llama 2, Gemma, Mixtral, vLLM, LangChain, RAG, ChromaDB, FAISS

This repository demonstrates how to fine-tune the Google Gemma 2 2B model to improve its performance on Japanese instruction-following tasks. It serves as a practical guide for developers and researchers interested in adapting large language models for specific languages or domains using state-of-the-art techniques in 2024.

Finetune LLaMA-2-7b-chat to perform safety evaluation of user-bot conversation

🤖一键部署，利用TTS与LLM将长文本小说转化为多角色音/视频。

temThis repository contains Gen AI projects that performs different tasks

Production-grade RLHF & post-training pipeline built from first principles in PyTorch. Features causal transformers, LoRA SFT, Bradley-Terry reward modeling, DPO, IPO, PPO with GAE, DeepSeek-R1 style GRPO reasoning, and automated statistical release gating.

Catch tokenizer mistakes before they break your fine-tune.

📝 Generate engaging stories using GPT-2, while exploring how different parameters shape creative text output in this hands-on AI project.

This is a Backporting LLM, for Azurelinux at Microsoft. It is an LLM finetuned on the Git Commit History of a Linux Package (Libsoup) using QLoRA (for local models) to Backport Upstream Patches to Old Version of the Package.

"FASHIO leverages FAISS and advanced NLP for precise fashion recommendations tailored to user preferences."