Louis's repositories
yolov5_torchserve
Torchserve server using a YoloV5 model running on docker with GPU and static batch inference to perform production ready and real time inference.
deep_gas_oracle
Unofficial implementation of the paper: "Step on the Gas? A Better Approach for Recommending the Ethereum Gas Price"
rat_crypto_trader
Relation-Aware Transformer for Portfolio Policy Learning using Binance provider
bert_timeseries
Multivariate time series representation learning (using bert-like model adapted for TS)
eip1559_analysis
Can we estimate the economic impact of EIP-1559 on miners? This repository try to estimate the loss of miners' revenue coming from transactions fees, using Ethereum historical data.
asymmetric_gaussian_nll_loss
Implementation of an asymmetric gaussian negative log likelihood loss for PyTorch.
enrichment_models
This repository benchmark Ntropy API against different Large Language Models (OpenAI ChatGPT and LLAMA finetuned models). It also contains an easy to use wrapper to enable using the LLMs to perform transaction enrichment. Llama adapters were open sourced and are available on huggingface hub.
multi-agent_soccerbot
Multi agent programming in java, using behaviour cascade, attraction repulsion systems, and bipolar attraction.
textClassification
NLP project done during the DECIM Master. Coorinated by Gael Lejeune (Maître de Conférences en Informatique).Classify newspaper by writing period.
tortv_on_demand
This is a tool that automatically create a temporary mail, create an account at TorTV with this temporary mail account and resolve the captcha using TemplateMatching.
Deep-Q-trading-cryptocurrencies
Master annual project that aims to make an agent able to trade on a cryptocurrency market and make benefits.
deepdow
Portfolio optimization with deep learning.
flyte-template
Template for creating Flyte workflows
garden-csp
Garden Layout Planner using Constraint Satisfaction Problem
langchain
⚡ Building applications with LLMs through composability ⚡
lit-gpt
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
serge
A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API.
tensorboardX
tensorboard for pytorch (and chainer, mxnet, numpy, ...)
vl53l1x-arduino
Pololu Arduino library for VL53L1X time-of-flight distance sensor