unsloth

There are 8 repositories under unsloth topic.

unsloth
unslothai / unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
agent deepseek deepseek-r1 fine-tuning gemma gemma3 gpt-oss llama llama3 llm llms mistral openai qwen qwen3 reinforcement-learning text-to-speech tts unsloth voice-cloning
Language:Python 48027
unslothai / notebooks
100+ Fine-tuning Tutorial Notebooks on Google Colab, Kaggle and more.
unsloth
Language:Jupyter Notebook 3803
GAD-cell / vlm-grpo
An implementation of GRPO for Unsloth's VLMs training
grpo grpotrainer huggingface trl unsloth vlm reinforcement-learning
Language:Python 75
sinanuozdemir / oreilly-pytorch-dl
Code for Deep Learning for Modern AI
bert deep-learning llama3 llms neural-networks distillation llama mnist quantization clip diffusion dreambooth dreambooth-finetuning multimodal unsloth
Language:Jupyter Notebook 45
qqqqqf-q / Qing-Digital-Self
数字分身项目,并且包含了搭建(复现)教程 Qing's digital self, including setup tutorial
ai chatbot llm qlora qwen unsloth ai-avatar digital-twin finetune finetune-llm huggingface personal-ai
Language:Python 33
Breeze648 / MedCoT-7B
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。
4-bit-quantization ai chain-of-thought deepseek-r1 distillation llm lora medical-application nlp qlora qwen unsloth
Language:Python 32
unsloth-llama3-alpaca-lora
Cre4T3Tiv3 / unsloth-llama3-alpaca-lora
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.
4bit alpaca colab finetuning gradio huggingface instruction-tuning llama3 llm lora open-source peft qlora transformers unsloth
Language:Jupyter Notebook 31
shaheennabi / Production-Ready-Instruction-Finetuning-of-Meta-Llama-3.2-3B-Instruct-Project
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 🎋
finetuning 4bit-quantize gguf huggingface meta qlora quantization deployed open-source production-ready unsloth gpu inference modular-code training bitsandbytes peft 4bitprecision anthropic-hh-golden unified-language-model-aligning
Language:Jupyter Notebook 23
SrikarVeluvali / Astor-AI
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.
flask huggingface llama3 llm mongodb ollama react transformers unsloth
Language:Jupyter Notebook 20
Eviltr0N / Make-AI-Clone-of-Yourself
Cloning Yourself using your whatsapp chat history and training a model on it.
ai ai-clones finetuning llama3 llama3-8b llama3-finetune llama3-rag unsloth whatsapp-bot whatsapp-clone whatsapp-python ai-project llm llm-project ollama
Language:Jupyter Notebook 19
0xZee / DeepSeek-R1-FineTuning
Fine-Tuning of DeepSeek-Style Reasoning Models | RL + Quantization Implementation
deepseek-r1 lora qlora reinforcement-learning unsloth
Language:Jupyter Notebook 17
Biomedical-Knowledge-Graph
alisonmitchell / Biomedical-Knowledge-Graph
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.
arxiv bertopic coreference-resolution europe-pmc grobid groq knowledge-graph llamaindex named-entity-recognition pdfminersix relation-extraction unsloth bern2 fastcoref kazu melodi-presto spacy-scispacy langchain biomedical drug-repurposing
Language:Jupyter Notebook 15
deep-div / Fine-Tuning-LLMs-and-VisionModels
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.
deepseek finetuning-llms gemma generative-ai huggingface large-language-models llama llama-factory llm transformers unsloth keras-finetuning
Language:Jupyter Notebook 14
QuangNguyen711 / AutClothingChatbot
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.
chatbot clothing langchain llm llms rag unsloth vector-database
Language:Jupyter Notebook 14
finetune-web-ui
muhammad-fiaz / finetune-web-ui
Finetune Web UI is a user-interface for training and deploying pre-trained models.
datasets fine-tuning finetune finetuning-llms generative-ai gpt huggingface large-language-models transformers unsloth finetune-gpt finetune-llms gradio finetune-web-ui
Language:Python 12
IAmSkyDra / finetune-quantize-llms
Materials for CSE Summer School Hackathon 2024
fine-tune llama-factory llms quantize unsloth
Language:Jupyter Notebook 11
bastienpo / unsloth_finetuning
Finetuning of Gemma-2 2B for structured output
ai fine-tuning gemma2 llamacpp python unsloth
Language:Jupyter Notebook 10
jkanalakis / finetuning-llama-model-for-text-generation-using-unsloth
Fine-tuning Llama 3.2 3B Instruct model for text generation using Unsloth AI
llama3 unsloth fine-tuning llm generative-ai text text-generation
Language:Jupyter Notebook 9
mirabdullahyaser / LLaMA3-Financial-Analyst
LLM-powered financial analyst using LoRA-tuned Llama-3 and RAG pipeline to answer complex queries over SEC 10-K filings with contextual accuracy.
embeddings fiass finance financial-analysis fine-tuning huggingface llama3 llm lora rag supervised-finetuning unsloth vector-database chatbot question-answering
Language:Jupyter Notebook 9
harshit433 / ResurrectAI
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
finetuning-llms firebase flask flutter html-css-javascript llama3-1 ollama python unsloth artificial-intelligence chatbot conversational-ai language-model machine-learning
Language:Dart 8
Asad-Shahab / sudokuLLM
LLM finetuning for Sudoku solving
grpo llm-training unsloth fine-tuning reasoning-models reinforcement-learning
Language:Python 7
hyeonsangjeon / PDF2LLM-Tuning-Studio
PDF 문서에서 GPU 가속 처리로 고품질 질의응답(QA) 데이터를 자동 생성하고 LLM을 효율적으로 파인튜닝하는 솔루션입니다. Unstructured 라이브러리와 AWS Bedrock Claude로 도메인 특화 QA 쌍을 생성하고, LoRA 기법으로 경량 모델을 훈련합니다.
awosome aws bedrock claude cuda data-argumantation data-extraction distillation docker finetuning gpu llm pdf-generation pdf-text-extraction processing processing-job sagemaker text-disti unsloth unstructured
Language:Jupyter Notebook 7
TheTrustyPwo / PwoAI
🤖 AI of Pwo fine tuned on Llama-3.1-8B Instruct
ai pwo finetune llama3 unsloth whatsapp
Language:Jupyter Notebook 6
xphot / app
Análise Avançada de Dados com Causalidade e Aprendizado por Reforço
bug-tracker causal-machine-learning experimental-psychology explainability-metric hypergraph-neural-network llms-reasoning data-preprocessing llm-fine-tuning reinforcement-learning shap-analysis unsloth gguf-quantization
Language:Jupyter Notebook 6
Akshint0407 / Nano-R1
This project demonstrates the process of fine-tuning the Qwen2.5-3B-Instruct model using GRPO (Generalized Reward Policy Optimization) on the GSM8K dataset.
adapters grpo huggingface python qwen2-5 safetensors text-generation-inference transformer trl unsloth
Language:Jupyter Notebook 5
PRAISELab-PicusLab / SOLVE-Med
⚕️ Multi-agent SLM system for medical question answering — domain-aware, private-by-design, cloud-free
fine-tuning gemma healthcare llama llm medical-ai multi-agent nlp question-answering slm unsloth specialist-models
Language:JavaScript 5
prodesk98 / SQL-LLM-Distillation-GRPO
Inspired by mathematical reasoning models like DeepSeekMath, this framework applies CoT to SQL generation and fine-tunes distilled models using GRPO to enhance both accuracy and interpretability.
chain-of-thought grpo llm reasoning sql text2sql unsloth
Language:Jupyter Notebook 5
ramona1999 / Contract-Risk-Assessment
This project is an AI-powered Contract Risk Assessment and Legal Assistant designed to analyze legal documents, extract key clauses, assess risks, and provide actionable recommendations. Additionally, a fine-tuned conversational chatbot is integrated for interactive legal Q&A based on contract-specific knowledge.
docling finetuning-llms langgraph milvus unsloth
Language:Jupyter Notebook 5
krish1925 / Persona-Chatbot-G28
Fine-tuning GPT-3.5 and Llama3 LLMs for enhanced persona consistency in chatbots using Google's Synthetic Persona Chat dataset
bertscore finetuning gpt-3-5-turbo llama3 perplexity persona-chatbot rouge-metric unsloth
Language:Jupyter Notebook 4
Pavansomisetty21 / Qwen2-Vision-Finetuning-Unsloth---Maths-OCR-Formulae-Extraction-
we finetune unsloth llama model to extract mathematical fomulas in the images with optical character recognition(OCR)
qwen2 llama llm maths ocr ocr-recognition optical-character-recognition qwen2-vl unsloth vision-language-model vlm
Language:Jupyter Notebook 4
Pavansomisetty21 / Visual-Question-Answering-Pixtral_Vision_Finetuning_Unsloth
In this we finetune Pixtral-12B-2409 model using unsloth for visual Question Answering(NLP Task)
fine-tuning large-language-models llm nlp pixtral unsloth vision-language-model visual-question-answering vlm
Language:Jupyter Notebook 4
yuki-2025 / llama3-8b-fine-tuning-math
Fine-Tuning Llama 3-8B for Structured Math Reasoning: Fine-tuning Llama3 8b to generate JSON formats for arithmetic questions and process the output to perform calculations.
fine-tuning huggingface llama llama3 peft-fine-tuning-llm qlora unsloth
Language:Python 4
Mattjesc / OS-Verilog-Copilot-FT-LLM-Unsloth
Open Source Verilog Copilot: Fine Tune LLM: Fine-Tuning LLM with QLoRA and VeriGen Dataset using Unsloth
ai fine-tuning finetuning llm qlora unsloth verilog
Language:Python 3
Siddhesh19991 / RAG_Medical_Data
This project demonstrates how to setup a complete Retrieval Augmented Generation (RAG) pipeline on medical data using Llama-3-8B model
ai langchain llama3 lllm rag unsloth mongodb-atlas
Language:Jupyter Notebook 3
Tommaso-Sgroi / VojoLe-LM
DL24-25 project. The goal is Fine-Tuning a LLM on Italian Dialect.
finetune finetuning finetuning-llms llm llms low-resource-languages unsloth vllm
Language:Jupyter Notebook 3
petermartens98 / GPT-OSS-20B-Multilingual-Reasoning-Fine-tune
GPT-OSS-20B fine-tuned for multilingual reasoning with LoRA (trained on Google Colab GPU). Trained on 1k Multilingual-Thinking samples across multiple languages Features 4-bit quantization and chain-of-thought reasoning. Optimized with Unsloth for efficient training.
fine-tuning gpt-oss-20b huggingface multi-lingual open-source reasoning unsloth
Language:Jupyter Notebook 2

unsloth

unslothai / unsloth

unslothai / notebooks

GAD-cell / vlm-grpo

sinanuozdemir / oreilly-pytorch-dl

qqqqqf-q / Qing-Digital-Self

Breeze648 / MedCoT-7B

Cre4T3Tiv3 / unsloth-llama3-alpaca-lora

shaheennabi / Production-Ready-Instruction-Finetuning-of-Meta-Llama-3.2-3B-Instruct-Project

SrikarVeluvali / Astor-AI

Eviltr0N / Make-AI-Clone-of-Yourself

0xZee / DeepSeek-R1-FineTuning

alisonmitchell / Biomedical-Knowledge-Graph

deep-div / Fine-Tuning-LLMs-and-VisionModels

QuangNguyen711 / AutClothingChatbot

muhammad-fiaz / finetune-web-ui

IAmSkyDra / finetune-quantize-llms

bastienpo / unsloth_finetuning

jkanalakis / finetuning-llama-model-for-text-generation-using-unsloth

mirabdullahyaser / LLaMA3-Financial-Analyst

harshit433 / ResurrectAI

Asad-Shahab / sudokuLLM

hyeonsangjeon / PDF2LLM-Tuning-Studio

TheTrustyPwo / PwoAI

xphot / app

Akshint0407 / Nano-R1

PRAISELab-PicusLab / SOLVE-Med

prodesk98 / SQL-LLM-Distillation-GRPO

ramona1999 / Contract-Risk-Assessment

krish1925 / Persona-Chatbot-G28

Pavansomisetty21 / Qwen2-Vision-Finetuning-Unsloth---Maths-OCR-Formulae-Extraction-

Pavansomisetty21 / Visual-Question-Answering-Pixtral_Vision_Finetuning_Unsloth

yuki-2025 / llama3-8b-fine-tuning-math

Mattjesc / OS-Verilog-Copilot-FT-LLM-Unsloth

Siddhesh19991 / RAG_Medical_Data

Tommaso-Sgroi / VojoLe-LM

petermartens98 / GPT-OSS-20B-Multilingual-Reasoning-Fine-tune