LLM based autonomous agent that conducts local and web research on any topic and generates a comprehensive report with citations.

Get your documents ready for gen AI

The framework for building scalable agentic applications.

Foundation Models for Time Series

Agentic components of the Llama Stack APIs

Composable building blocks to build Llama Apps

🦄 Unitxt: a python library for getting data fired up and set for training and evaluation

A modular graph-based Retrieval-Augmented Generation (RAG) system

Granite Code Models: A Family of Open Foundation Models for Code Intelligence

A python module to repair invalid JSON, commonly used to parse the output of LLMs

InstructLab Command-Line Interface. Use this to chat with a model and execute the InstructLab workflow to train a model using custom taxonomy data.

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

orchestrate ML model deployments, monitoring and governance for Cloud Pak for Data and other Data & AI platforms faster.

🐢 Open-Source Evaluation & Testing for AI & LLM systems

Notebooks & Example Apps for Search & AI Applications with Elasticsearch

Public repo for HF blog posts

Code and documentation to train Stanford's Alpaca models, and generate the data.

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Efficient Retrieval Augmentation and Generation Framework

Build Enterprise RAG (Retriver Augmented Generation) Pipelines to tackle various Generative AI use cases with LLM's by simply plugging componants like Lego pieces. This repo is intended for IBM Eco…

Code Transformer neural network components piece by piece

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

Python bindings for llama.cpp

LLM inference in C/C++

The simplest, fastest repository for training/finetuning medium-sized GPTs.

A concise but complete full-attention transformer with a set of promising experimental features from various papers

Examples using the Deep Search functionalities

The prime repository for state-of-the-art Multilingual Question Answering research and development.