unsloth

LLM-powered financial analyst using LoRA-tuned Llama-3 and RAG pipeline to answer complex queries over SEC 10-K filings with contextual accuracy.

LLM finetuning for Sudoku solving

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.

Low-Resource LLM Fine-Tuning using Unsloth and LoRA/QLoRA (WSL2/Linux) 🧠

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

Adversarial LLM arena using GRPO + SFT to train a model that generates questions hard LLMs can't solve

Finetuning of Gemma-2 2B for structured output

7.67× LoRA / 8.35× Full FT speedup for Qwen3.5 (0.8B–27B) on NVIDIA DGX Spark — wall-clock parity with rented H100. Lossless within BF16. Three-command interactive wizard handles model picker, data validator, training, and merge.

⚕️ Multi-agent SLM system for medical question answering — domain-aware, private-by-design, cloud-free

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