Stars
HISTDATA - Dataset composed of all FX trading pairs / Crude Oil / Stock Indexes. Simple API to retrieve 1 Minute data (and tick data) Historical FX Prices (up to date).
Investment Research for Everyone, Everywhere.
A simple and efficient tool to parallelize Pandas operations on all available CPUs
Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight), https://openreview.net/forum?id=JePfAI8fah
A custom pytorch Dataset extension that provides a faster iteration and better RAM usage
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Implementation of Graph Transformer in Pytorch, for potential use in replicating Alphafold2
Multi-dimensional/Multi-input/Multi-output Data preprocessing and Batch Generators for Keras models
Training efficient drone controllers with Analytic Policy Gradient
A free and simple cryptocurrency sentiment analysis API
Simple, hackable and fast implementation for training/finetuning medium-sized LLaMA-based models
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
DSIR large-scale data selection framework for language model training
Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"
This repo is the home of Romanian Transformers.
all scripts used in gatortron project
A framework for few-shot evaluation of language models.
Code for hierarchical imitation learning and reinforcement learning
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
🆔 A python library for accurate and scalable fuzzy matching, record deduplication and entity-resolution.
VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
Language model alignment-focused deep learning curriculum
Hierarchical Image Pyramid Transformer - CVPR 2022 (Oral)
This Python module can be used to obtain antonyms, synonyms, hypernyms, hyponyms, homophones and definitions.