Chat with AI large language models running natively in your browser. Enjoy private, server-free, seamless AI conversations.

Grimoire is All You Need for Enhancing Large Language Models

A branch of sgminer optimized with GCN cross lane instructions on AMD (ethash, phi2, lyra2Z[z], allium, x25x, lyra2REv2/v3, argon2d, yescrypt, neoscrypt, 0x10)

onenm_local_llm is a Flutter plugin that simplifies on-device language model inference on Android using llama.cpp. It removes the complexity of setting up native runtimes, model loading, and inference pipelines, so developers can integrate local AI into their apps through a simple API.

A text-to-audio application that turns words and sentiments into melodies.

A project for fine-tuning large language models (LLMs) on curated Wikipedia datasets, featuring data preprocessing, model training with Phi-2, and evaluation using Python and Jupyter notebooks.

This project evaluates and compares two LLMs on various software engineering tasks, including code generation, test generation, and documentation. The models used are phi-2 and Cohere Command.

Offline AI-powered Linux assistant using a fine-tuned Phi-2 model with Ollama, enabling natural language interaction and command suggestions directly in the terminal.

Fine-tuning Phi-2 with LoRA for grid-based spatial reasoning and Chain-of-Thought (CoT) inference.

An intelligent hologram-based AI assistant for retail, developed as a Final Year Project to deliver interactive customer engagement and smart product guidance.

Use of phi2 for custom use.

A QLoRa approach to teach Persian reasoning to Phi2-microsoft

AI Comedian

End-to-end healthcare LLM system using Phi-2 + QLoRA (4-bit quantization) with FastAPI inference API.

Using the Group News 20 dataset, this project employs the microsoft/phi1.5 model for text classification via prompting. We redefine classification as label generation, evaluating results with standard metrics and uploading the model on HuggingFace

Fine-tuning Microsoft’s Phi-2 model using QLoRA on the Alpaca-cleaned dataset with 4-bit quantization (bitsandbytes).

Projekt u sklopu predmeta Obrada prirodnog jezika

🧬 A Study & Web Application Exploring the Capabilities of LLMs in Cross-Language Code Translation

LLM Prompt Recovery