matthieuvion

matthieuvion

Geek Repo

Location:Paris

Github PK Tool:Github PK Tool

matthieuvion's starred repositories

EdgeGPT

Reverse engineered API of Microsoft's Bing Chat AI

Language:PythonLicense:UnlicenseStargazers:8070Issues:92Issues:364

setfit

Efficient few-shot learning with Sentence Transformers

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:2225Issues:21Issues:318

gpu-jupyter

GPU-Jupyter: Leverage the flexibility of Jupyterlab through the power of your NVIDIA GPU to run your code from Tensorflow and Pytorch in collaborative notebooks on the GPU.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:708Issues:17Issues:96

Awesome-TimeSeries-SpatioTemporal-Diffusion-Model

A survey and paper list of current Diffusion Model for Time Series and SpatioTemporal Data with awesome resources (paper, application, review, survey, etc.).

Awesome-TimeSeries-LLM-FM

The collection of resources about LLM for Time series tasks

london_rightmove

Production ML rental prediction system.

Language:Jupyter NotebookStargazers:28Issues:2Issues:0

github_ci_nbconvert

Convert notebook (*.ipynb) files using Github Actions automatically after each commit and access HTML outputs with a public URL using Github Pages

Language:Jupyter NotebookLicense:MITStargazers:14Issues:2Issues:0

en-fr-translation-service

Dummy project to create an English/French translation service using Hugging Face, Docker and such.

MonsterTrainGameData

Data dumps for Monster Train game data, so that AssetStudio no longer needs to be used.

lmd_ukr

Custom dataset of Le Monde (236 k comments), 1-year-coverage-on-Ukraine & custom made associated API (need Subscriber credentials)

Language:PythonStargazers:4Issues:1Issues:0

lmd_viz

https://matthieuvion.github.io/lmd_viz/ 236k comments of Le Monde on Ukraine. A proxy to measure people' engagement. Semantic search & SBERT models testing via Sentence-Transformer / Faiss

Language:HTMLStargazers:4Issues:1Issues:0

wzkd

Streamlit-based dashboard that collect, aggr. and visualize player's stats from Call of Duty Warzone1. Also deploy our model (cf. /match2kd repo) to predict game difficulty ("lobby kd") from game features.

Language:PythonStargazers:4Issues:1Issues:0

match2kd

Save thousands of API calls. Custom model & dataset aiming at predicting a game difficulty score ("lobby avg kd") without calling players' games history stats and profiles.

Language:Jupyter NotebookStargazers:3Issues:1Issues:0

wzlight

Light asynchronous wrapper for COD Warzone (1) API. Available on PyPi.

Language:PythonStargazers:3Issues:1Issues:0

lmd_classi

Classifier(s). Complete guide SetFit vs fine-tuned Mistral-7B vs. quantized ONNX model based on multi-e5 embeddings

Language:Jupyter NotebookStargazers:2Issues:1Issues:0

databricks-xgb

Distributed XGB on Spark with MLFlow model tracking. Code & notes on compatibility of (3!) XGB variants with PySpark/Databricks/MLFlow. Ensure notebook works with Community Edition.

Language:Jupyter NotebookStargazers:1Issues:1Issues:0

lstm-gpu-jupyter

LSTM (PyTorch) , time series prediction: a benchmark case w/ and w/o stationarity + scaling

Language:Jupyter NotebookStargazers:1Issues:1Issues:0

mt-leaderboard

Just to crunch some stats. Reverse engineering unofficial/undocumented API for Monster Train (game) daily challenge scoreboards.

Language:C#Stargazers:1Issues:1Issues:0

spark-cluster

Steps to deploy a local spark cluster w/ Docker. Bonus: a ready-to-use notebook for model prediction on Pyspark using spark.ml Pipeline() on a well known dataset

Language:Jupyter NotebookStargazers:1Issues:1Issues:0