ebergel Goto Github PK

alpaca-collab-

alpaca.cpp

Locally run an Instruction-Tuned Chat-Style LLM

ancmozambique

Interactive Stepped-Wedge Cluster Randomised Trial Data Analysis Tool

auto-gpt

An experimental open-source attempt to make GPT-4 fully autonomous.

autotemp

A trial-and-error approach to temperature opimization for LLMs. Runs the same prompt at many temperatures and selects the best output automatically.

buenosaires2018

Workshop for Buenos Aires on 11 May 2018

claude-dev

Claude Dev goes beyond simple code completion by reading & writing files, creating projects, and executing terminal commands with your permission.

comfyui

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

constellationfinder

Finds patterns in the Collatz Tree

contrastive_metrics

dalai

The simplest way to run LLaMA on your local machine

dndi.bendita.ni.analysis

Non inferiority analysis for BENDITA trial

egregoria

3D City Builder without a grid

fbi-llm

FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation

finetuning

Finetune Llama-3-8b on the MathInstruct dataset

flash-attention

Fast and memory-efficient exact attention

gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

gpt4all

gpt4all: a chatbot trained on a massive collection of clean assistant data including code, stories and dialogue

graph-of-thoughts

Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"

iecs.indicadores

indicadores validation, hardvard, gates

litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

llama

Inference code for LLaMA models

llama-chat

Chat with Meta's LLaMA models at home made easy

llama-dl

High-speed download of LLaMA, Facebook's 65B parameter GPT model

llm.c

LLM training in simple, raw C/CUDA

lme4

Mixed-effects models in R using S4 classes and methods with RcppEigen

machine-learning-for-software-engineers

A complete daily plan for studying to become a machine learning engineer.

mem0

The memory layer for Personalized AI

metagpt

🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo

minbpe

Minimal, clean, code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.