unsloth

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

100+ Fine-tuning LLM Notebooks on Google Colab, Kaggle, and more.

Create large-scale synthetic training data for model distillation and evaluation

Make Llama 3.1 8B talk in Rick Sanchez’s style

An implementation of GRPO for Unsloth's VLMs training

Code for Deep Learning for Modern AI

本项目利用医学领域的 CoT 数据对 Deepseek-R1-Distill-Qwen-7B 进行微调，通过 QLoRA 量化和 Unsloth 加速训练，显著提升模型在复杂医学推理任务中的慢思考能力。知识蒸馏技术使轻量级模型获得大模型的推理优势，实现高效、准确且具有解释性的医学问答系统。

数字分身项目,并且包含了搭建(复现)教程 Qing's digital self, including setup tutorial

Advanced 4-bit QLoRA fine-tuning pipeline for LLaMA 3 8B with production-grade optimization. Memory-efficient training on consumer GPUs for instruction-following specialization. Demonstrates cutting-edge parameter-efficient fine-tuning with Unsloth integration.

Instruction Fine-Tuning of Meta Llama 3.2-3B Instruct on Kannada Conversations. Tailoring the model to follow specific instructions in Kannada, enhancing its ability to generate relevant, context-aware responses based on conversational inputs. Using the Kannada Instruct dataset for fine-tuning! Happy Finetuning 🎋

Cloning Yourself using your whatsapp chat history and training a model on it.

Fine-Tuning of DeepSeek-Style Reasoning Models | RL + Quantization Implementation

Fine-Tuning LLMs (Gemma, LLaMA, Mistral, etc.) A practical guide to fine-tuning various large language models using popular frameworks. Includes examples, scripts, and tips for efficient training on custom datasets.

Information extraction from unstructured text to build a knowledge graph using techniques from traditional NLP to pre-trained transformers and LLMs for NER and Linking, and Relation Extraction.

PTIT's Major Project: Website Programming - This repo contains a chatbot for a clothing store. The chatbot acts as an employee with specific knowledge about clothing consultation, website support, and store information.

Finetune Web UI is a user-interface for training and deploying pre-trained models.

Materials for CSE Summer School Hackathon 2024

AstorAI is a user-friendly medical chatbot powered by Retrieval-Augmented Generation (RAG) and the advanced LLama 3 model. It offers real-time, accurate responses to a wide range of medical queries, ensuring privacy and security in every interaction. Designed for ease of use, AstorAI provides reliable health information on various topics 24/7.

Finetuning of Gemma-2 2B for structured output

Fine-tuning Llama 3.2 3B Instruct model for text generation using Unsloth AI