syncdoth Goto Github PK

an-application-of-deep-reinforcement-learning-to-algorithmic-trading

Experimental code supporting the results presented in the scientific research paper entitled "An Application of Deep Reinforcement Learning to Algorithmic Trading"

bittensor

Internet-scale Neural Networks

chain-of-hindsight-pytorch

Unofficial implementation of Chain of Hindsight (https://arxiv.org/abs/2302.02676) using pytorch and huggingface Trainers.

cold_decoding

colossalai

Making large AI models cheaper, faster and more accessible

comet-rl

A WIP project of training COMET model using RL.

covid-19-ner

darkroom

diffusion-lm

Diffusion-LM

dsi-transformers

A huggingface transformers implementation of "Transformer Memory as a Differentiable Search Index"

eagle-eye-pneumonia-detection

ecco

Visualize and explore NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2).

export_ig

A pip package for exporting images for Instagram: add padding around image + drop shadow for instagram upload.

ey_datawave_challenge

face_mask_inpaint

GAN-based project of removing facial masks from face images.

force-rnn

gradio_serving

Simple example of using gradio for serving ML models.

gravity-modulator

Gravity Modulator that on Python Turtle environment. Simple Interface with a bouncy ball, a piston, and Force input.

hkust-ksa-ml-study

HKUST KSA 2020 ML study repository

hkust_phd_mphil_thesis_latex

The Hong Kong University of Science and Technology PhD/MPhil thesis latex template based on the latest official sample (http://pg.ust.hk/guides_n_forms/students/thesis_sample_page_phd.pdf)

jekyll-pygments-themes

CSS themes for Pygments syntax highlighter, ready to drop into Jekyll. Also includes a custom theme builder!

litgpt

Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.

mafia-explanation-nli

Official code for MAFIA (MAsk-based Feature Interaction Attribution): Explain BERT model's decision in NLI task.

mrc_serve

Procedure for serving Pororo (https://github.com/kakaobrain/pororo) pretrained models using torchserve.

myassetmange

nlp-tdsc

COMP 5331 HKUST Team 16

predicting-business-popularity

About Research project on predicting business popularity using GNNs in location-based social networks.

pretraining

Pretraining

prompt-compression

This is an unofficial implementation of prompt-compression for my own research.

retnet

Huggingface compatible implementation of RetNet (Retentive Networks, https://arxiv.org/pdf/2307.08621.pdf) including parallel, recurrent, and chunkwise forward.