fine

Awesome Reasoning LLM Tutorial/Survey/Guide

Train Large Language Models on MLX.

Tools made for usage alongside artistic style transfer projects

RAFT, or Retrieval-Augmented Fine-Tuning, is a method comprising of a fine-tuning and a RAG-based retrieval phase. It is particularly suited for the creation of agents that realistically emulate a specific human target.

🍎👉🍏 Everything you need in order to get started building distributed machine learning with Apple's MLX

DantinoX: A modular, memory-efficient Transformer implementation in JAX/Flax NNX. Includes Sparse MoE, GQA, Sliding Window Attention, Gradient Accumulation and Checkpointing

Proyek Ollama DeepSeek Llama RAG (Retrieval-Augmented Generation) - Fine-Tuned Proyek ini bertujuan untuk membuat sebuah Generative AI yang dapat membuat sebuah module ajar yang dapat digunakan oleh guru untuk mengajar siswa.

Retrieval-augmented multi-agent VQA system for radiology using QLoRA fine-tuned LLaVA-Next 7B, hybrid BM25+FAISS retrieval, and calibrated confidence estimation

PyDownloader is a new python script app to download requirement and enjoy the python!

This is the official repository of Debangan Ghosh. Here I made a Streamlit App for my Fine tuned ML prediction models for MASAI Hackathon

A photonic toroidal vortex model for calculating hydrogen atom hyperfine levels

Fine-tuning a pretrained self-supervised contrastive learning model for pneumonia classification, benchmarked against supervised learning models.

Fine-tuning and RAG study focused on generating structured and consistent AI responses with external context.

LoRA fine-tuning pipeline for Phi-3-mini on procurement data — QLoRA training + HF→GGUF conversion + Ollama deployment.