AdrianBZG/LLM-distributed-finetune

Stars
50
Rank 577,233 (Top 12 %)
Language
Python
License
MIT License
Created over 1 year ago
Updated over 1 year ago

AdrianBZG/LLM-distributed-finetune

AdrianBZG

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Tune efficiently any LLM model from HuggingFace using distributed training (multiple GPU) and DeepSpeed. Uses Ray AIR to orchestrate the training on multiple AWS GPU instances

Twitter-Follow-Exploit

Automated Twitter mass account creation and follow using Selenium and Tor VPN

llama-multimodal-vqa

Multimodal Instruction Tuning for Llama 3

Polyglotter

Code for "Translating synthetic natural language to database queries: a polyglot deep learning framework" (Nature Scientific Reports, 2021)

Medieval_Warfare_VR-Unity

Virtual Reality game for the Intelligent Interfaces subject, made with Unity Engine.

HyperBERT

Code for "HyperBERT: Mixing Hypergraph-Aware Layers with Language Models for Node Classification on Text-Attributed Hypergraphs"

N_Queens_Puzzle

This repo stores the N Queens Problem solution written in Java, developed for the subject "Development of Interactive Applications", assignment 6. Date: 30/03/2016

Algorithms-and-Data-Structures-II-2014

Codes for the subject "Advanced Algorithms and Data Structures". Language: C++

Muscular-Dystrophy-Diagnosis

Code for "A Convolutional Neural Network for the automatic diagnosis of collagen VI-related muscular dystrophies" (Applied Soft Computing, 2019)

WindPower-Data_Analysis

This is a Data Analysis tool/project to estimate whether a country can increase it's wind energy production (Using the difference between current wind energy produced and the possible wind energy that can produce if you build more Wind farms; using available terrain data) [read README.md]. Lecture PDF: http://adrianbazaga.info/pdf/WindPower_Lecture.pdf

SQLformer

Code for "SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL Translation"

Ruby_Codes-2015

Languages & Paradigms of Programming subject assessments codes. Language: Ruby

SFAVEL

Code for "Unsupervised Pretraining for Fact Verification by Language Model Distillation" (ICLR 2024)

InterMine-Data-Browser-Tool

InterMine Data Browser: a tool for exploring semi-homogeneous biological datasets

Framework_Divide-and-Conquer

Framework to solve Divide and Conquer problems in an easy way, you just need to define the specific Problem characteristics and the Framework will solve it for you with a D&C approach

PhoneChat

PhoneChat: Multimodal Interface Project for the Intelligent Interfaces subject

Markov_Random-Walk_Algorithm

Markov 2-dimensional random walk implementation. Language: Java. More info: https://en.wikipedia.org/wiki/Random_walk

ChuchuPlusPlus

Chuchu++ is a language/grammar built using PEGjs as parser and with it's own code generator, for the Language Processors subject

Multiuser-Chat-SharedMemory-2014

Multiuser chat using Shared Memory, for the Operating Systems subject. Language: C++. Using Qt

Tweet_NLP_Classification

Text classification for 'relevant' or 'not relevant' tweets (in terms of "natural disasters") using Natural Language Processing. Subject: Advanced Artificial Intelligence

Pushdown_Automaton

Pushdown Automaton with Graphical Interface

outreachy-opennmt-task

Design_Patterns_Example_Codes

This repo stores the Java codes and UML diagrams of the examples used for the lecture about "Design Patterns" by Adrián Rodríguez Bazaga and Rudolf Cicko, in University of La Laguna (Monday 28 March 2016)

IEMLS

Interactive Environment & Machine Learning Simulator (IEMLS) for scientific and educational purposes

Conway_Game-of-Life

John Conway's Game of Life implementation (cellular automaton), with GUI. Language: Java. More info: https://en.wikipedia.org/wiki/Conway%27s_Game_of_Life

QuickHull_Algorithm

QuickHull algorithm implementation, with graphical visualization. Language: Java. More info: https://en.wikipedia.org/wiki/Quickhull

CancerTargetPrediction

Code for the manuscript "Genome-wide investigation of gene-cancer associations for the prediction of novel therapeutic targets in oncology"

RAM-Machine-Simulator

RAM Machine Simulator v1.0. Doc: http://adrianbzg.github.io/RAM-Machine-Simulator/html/

bluegenes-depmap-cnv-visualizer

Visualizer for DepMap Copy Number Variation data per lineage for BlueGenes

storm-bio-sources

Turing_Machine

Multi-Tape Turing Machine with Graphical Interface. Language: Java

bluegenes-depmap-expression-visualizer

Visualizer for DepMap mRNA expression data per lineage for BlueGenes

personal_website

My personal website, deployed using Docker

TabMDA

Code for "TabMDA: Tabular Manifold Data Augmentation for Any Classifier using Transformers with In-context Subsetting" (ICML 2024)

tinyroberta-distillation-qa-es

Code for "Language Model Knowledge Distillation for Efficient Question Answering in Spanish" (ICLR 2024 Tiny Papers)