Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.
Collection of PDF parsing libraries like AI based docling, claude, openai, gemini, meta's llama-vision, unstructured-io, and pdfminer, pymupdf, pdfplumber etc for efficient snapshot, text, table, and metadata extraction.
MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Transformers — with support for 300+ large language models (Qwen3-Next, GLM-5.2, Deepseek-V4, MiniMax-2.7, ...) and 200+ multimodal large models (Qwen3.5, Qwen3-Omni, Gemma4, ...).
Rushikesh Nimkar's portfolio, accessible at rushikeshnimkar.xyz, is a modern website built with Next.js 15 and TypeScript. It features AI-powered email generation, an interactive chat with an AI version of Rushikesh, dynamic animations, responsive design, dark mode, and showcases his projects and contributions.
An intelligent travel planning application that uses HuggingFace's Llama 4 model to generate personalized travel itineraries and research destinations. Built with Streamlit for an intuitive web interface.
Chrome extension with Llama 4 multi-modal AI via Groq's fast inference. Chat with AI and analyze webpages directly in your browser.
Comprehensive benchmark of 44 open source language models across creative writing, logic puzzles, counterfactual reasoning, and programming tasks. Tested on Apple M4 Max with detailed performance analysis.
This project demonstrates three progressively advanced approaches to converting unstructured data into structured formats using AI
Pong game in the browser w/ realtime hand tracking, 3 difficulty levels, and 1-2 player options
🤖 Power your chats with BarkSuckerbird, a versatile Telegram bot that uses AI models and live web search for instant insights and support.
Chrome extension with Llama 4 multi-modal AI via Groq's fast inference. Chat with AI and analyze webpages directly in your browser.
A powerful Telegram AI bot that integrates multiple AI models, live web search via DuckDuckGo + Groq, and an admin texting system. It’s designed for 24/7 uptime using Flask’s keep-alive mechanism — perfect for deployment on Replit, Render, Koyeb or Railway.
💊 An elite clinical safety terminal that transforms handwritten prescriptions into structured medical intelligence in under 50ms. Powered by Groq Llama-4 Vision, Next.js 15, and NIH RxNav for real-time biometric tracking and drug interaction validation.
To associate your repository with the llama4 topic, visit your repo's landing page and select "manage topics."