Lucas O. Souza (lucasosouza)

lucasosouza

Geek Repo

Company:Numenta

Location:San Francisco, California, USA

Home Page:linkedin.com/in/lucasosouza/

Twitter:@lucasosouza

Github PK Tool:Github PK Tool

Lucas O. Souza's starred repositories

Mixture-of-depths

Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"

Language:PythonStargazers:112Issues:0Issues:0

LLM-RLHF-Tuning-with-PPO-and-DPO

Comprehensive toolkit for Reinforcement Learning from Human Feedback (RLHF) training, featuring instruction fine-tuning, reward model training, and support for PPO and DPO algorithms with various configurations for the Alpaca, LLaMA, and LLaMA2 models.

Language:PythonStargazers:95Issues:0Issues:0

optimum-habana

Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)

Language:PythonLicense:Apache-2.0Stargazers:130Issues:0Issues:0

openplayground

An LLM playground you can run on your laptop

Language:TypeScriptLicense:MITStargazers:6165Issues:0Issues:0

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Language:PythonLicense:MITStargazers:6373Issues:0Issues:0

curated-transformers

🤖 A PyTorch library of curated Transformer models and their composable components

Language:PythonLicense:MITStargazers:855Issues:0Issues:0

graph-of-thoughts

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

Language:PythonLicense:NOASSERTIONStargazers:1990Issues:0Issues:0

Promptify

Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:3125Issues:0Issues:0

Alpaca-CoT

We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台,我们欢迎开源爱好者发起任何有意义的pr!

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:2526Issues:0Issues:0

awesome-totally-open-chatgpt

A list of totally open alternatives to ChatGPT

License:CC0-1.0Stargazers:4469Issues:0Issues:0

awesome-instruction-dataset

A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

Stargazers:1044Issues:0Issues:0

pandas-ai

Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.

Language:PythonLicense:NOASSERTIONStargazers:12056Issues:0Issues:0

PaLM

An open-source implementation of Google's PaLM models

Language:PythonLicense:MITStargazers:803Issues:0Issues:0

openai-cookbook

Examples and guides for using the OpenAI API

Language:MDXLicense:MITStargazers:57704Issues:0Issues:0

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

Language:PythonLicense:MITStargazers:23379Issues:0Issues:0

lm-evaluation-harness

A framework for few-shot evaluation of language models.

Language:PythonLicense:MITStargazers:5879Issues:0Issues:0

evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Language:PythonLicense:NOASSERTIONStargazers:14397Issues:0Issues:0

llama

Inference code for Llama models

Language:PythonLicense:NOASSERTIONStargazers:54271Issues:0Issues:0

composer

Supercharge Your Model Training

Language:PythonLicense:Apache-2.0Stargazers:5074Issues:0Issues:0

data-preparation

Code used for sourcing and cleaning the BigScience ROOTS corpus

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:291Issues:0Issues:0

olm-datasets

Pipeline for pulling and processing online language model pretraining data from the web

Language:PythonLicense:Apache-2.0Stargazers:170Issues:0Issues:0

x-transformers

A simple but complete full-attention transformer with a set of promising experimental features from various papers

Language:PythonLicense:MITStargazers:4393Issues:0Issues:0

diffusion-models-class

Materials for the Hugging Face Diffusion Models Course

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:3400Issues:0Issues:0

bertviz

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

Language:PythonLicense:Apache-2.0Stargazers:6608Issues:0Issues:0

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Language:PythonLicense:NOASSERTIONStargazers:4941Issues:0Issues:0

uvadlc_notebooks

Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023

Language:Jupyter NotebookLicense:MITStargazers:2336Issues:0Issues:0

WeightWatcher

The WeightWatcher tool for predicting the accuracy of Deep Neural Networks

Language:PythonLicense:Apache-2.0Stargazers:1415Issues:0Issues:0

the-incredible-pytorch

The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

License:MITStargazers:11200Issues:0Issues:0

deep_learning_curriculum

Language model alignment-focused deep learning curriculum

Stargazers:1167Issues:0Issues:0

Tensor-Puzzles

Solve puzzles. Improve your pytorch.

Language:Jupyter NotebookLicense:MITStargazers:2934Issues:0Issues:0