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

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

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

Train YOLO + VLM with one command. Auto-generate vision-language training data from YOLO labels - no extra labeling needed.

Jupyter notebooks for course Finetuning Large Language Models, taught by Sharon Zhou (Lamini) and Andrew Ng (DeepLearning.AI).

This Repo Contains Script To Fine Tune Open Source Models Using Unsloth by using UI with simple click and progress

A fine-tuned version of SmolLM2-360M-Instruct-bnb-4bit specialized for parsing unstructured calendar event requests into structured JSON data.

A Python script to analyze images generated using a LoRA (Low-Rank Adaptation) model applied at various strength levels. This tool helps determine an optimal strength for a given LoRA by evaluating image quality and similarity to control images.

An AI powered chat bot to deal with mental health problems, which includes the concepts of RAG, Fine tuning and Graph Database.

🔧 Modular pipeline for generating high-quality, domain-specific datasets for LLM fine-tuning — from PDFs and web scraping to synthetic Q&A generation, quality filtering, and training-ready formatting.

Training & Finetune Salamandra 7B

This repo is about learning LLM from scratch. It includes all the foundation or core concept required for LLM understanding from beginner to practioner level

(In-progress) Finetuning OpenAI's GPT-3.5-Turbo as a base model on open-source data about the Tampa Bay region to create a chatbot specializing in information on the area!

"AI-powered CV ranking pipeline with fine-tuned embeddings, pgvector storage and OCR handling"

Worked on projects @ BNL as part of the Dept. Of Energy’s SULI program, focusing on KBASE, an open-source biological knowledge base.

project demonstrates an Abstractive Question Answering (QA) system built using t5-small model.

System-Level Efficient Processing of Llama3.2-1B

This platform lets user collect LLM response correction feedback, curate datasets generate JSONL and QLoRA adapters on-demand using GPU jobs, without retraining full models.

End-to-end QLoRA finetuning workflow on Llama 3.1 8B — distil a dataset with Claude, human-curate it, train a rank-16 LoRA adapter on Modal, and A/B-eval against the base model with an LLM judge (BI-fluency +0.92). A DAX-to-English explainer for Power BI, shipped as three linked artifacts: GitHub + HF model + HF dataset.