#
farshadniazi
Follow
Starred repositories
A natural language interface for computers
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.
Making large AI models cheaper, faster and more accessible
A high-performance, zero-overhead, extensible Python compiler using LLVM
Stable Diffusion web UI
devCellPy is a Python package designed for hierarchical multilayered classification of cells based on single-cell RNA-sequencing.
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.
CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.
Low-code framework for building custom LLMs, neural networks, and other AI models
Python implementation of the Loom file format - http://loompy.org
Guide to using pre-trained large language models of source code
Code and example data for running Consensus Non-negative Matrix Factorization on single-cell RNA-Seq data
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).
Distributed and decentralized training framework for PyTorch over graph
Plenoxels: Radiance Fields without Neural Networks
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
8-bit systems to ESP32 WiFi Multifunction Firmware
Cockpit: A Practical Debugging Tool for Training Deep Neural Networks
Digital logic design tool and simulator
A digital logic designer and circuit simulator.
Lecture notes, tutorial tasks including solutions as well as online videos for the reinforcement learning course hosted by Paderborn University
Cross-platform, customizable ML solutions for live and streaming media.
This is a Computer vision package that makes its easy to run Image processing and AI functions. At the core it uses OpenCV and Mediapipe libraries.
Model parallel transformers in JAX and Haiku