lipovsek
Follow
Stars
An open collection of methodologies to help with successful training of large language models.
Jupyter Notebook extension leveraging pandas DataFrames by integrating DataTables and ChartJS.
AI code-writing assistant that understands data content
⚡️Optimizing einsum functions in NumPy, Tensorflow, Dask, and more with contraction order optimization.
A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.
An open source implementation of CLIP.
An open-source efficient deep learning framework/compiler, written in python.
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
Experiments with Model Training, Deployment & Monitoring
WebChatGPT: A browser extension that augments your ChatGPT prompts with web results.
Accessible large language models via k-bit quantization for PyTorch.
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
Power CLI and Workflow manager for LLMs (core package)
Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation (CVPR 2023)
Implementation of Phenaki Video, which uses Mask GIT to produce text guided videos of up to 2 minutes in length, in Pytorch
Implementation of Chroma, generative models of protein using DDPM and GNNs, in Pytorch
contaiNERD CTL - Docker-compatible CLI for containerd, with support for Compose, Rootless, eStargz, OCIcrypt, IPFS, ...
Pytorch library for fast transformer implementations
🔥 horizontally-scalable, highly-available, multi-tenant continuous profiling aggregation system
Amazon Q, CodeCatalyst, Local Lambda debug, SAM/CFN syntax, ECS Terminal, AWS resources
Fast Inference Solutions for BLOOM
Fast and memory-efficient exact attention
Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"