marcinja

stable-diffusion-webui

Stable Diffusion web UI

llama_index

LlamaIndex is a data framework for your LLM applications

py-spy

Sampling profiler for Python programs

open-llms

📋 A list of open LLMs available for commercial use.

dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.

llama-recipes

Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger

abcd

harpoon

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

reth

Modular, contributor-friendly and blazing-fast implementation of the Ethereum protocol, in Rust

fully-homomorphic-encryption

An FHE compiler for C++

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

fzf-lua

Improved fzf.vim written in lua

maud

:pencil: Compile-time HTML templates for Rust

ml-fastvit

This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023

efm-langserver

General purpose Language Server

cryo

cryo is the easiest way to extract blockchain data to parquet, csv, json, or python dataframes

loom

Multiversal tree writing interface for human-AI collaboration

flux

Graph-based LLM power tool for exploring many completions in parallel.

core

High-performance, well-tested & documented core libraries for Ethereum, in Rust

reflect

Compile-time reflection API for developing robust procedural macros (proof of concept)

LLM-Reading-List

LLM papers I'm reading, mostly on inference and model compression

mpt-30B-inference

Run inference on MPT-30B using CPU

chain-registry

flood

flood is a load testing tool for benchmarking EVM nodes over RPC

transpeeder

train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism

loom

a socketteer/loom reimplementation in obsidian

reth-db-py

Python wrapper around reth db. Written in Rust.

jaxite

fresh-blog

A minimal blog template using the Fresh framework for Deno.