Skip to content
View pcrespan's full-sized avatar

Block or report pcrespan

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
pcrespan/README.md

🖥️ Pedro Crespan

Machine Learning Engineer

Hello! I'm a Machine Learning Engineer at Tractian, specializing in performance, model deployment, monitoring and data processing. I'm currently an undergraduate in Information Systems at São Paulo State University (UNESP), where I am deepening my knowledge in core concepts.

Naturally curious and passionate about solving complex problems, I am always striving for excellence. My constant motivation is to learn and apply innovative approaches to improve processes and create impactful solutions.

loc linkedin researchgate


🔨 Languages & other

Python

Torch

Docker

Go

postgres

Redis

linux

fastapi



📌 Statistics

GitHub Stats

GitHub Stats

Pinned Loading

  1. Baymed-RAS Baymed-RAS Public

    Medical project to help doctors identify a patient's disease based on symptoms sent to an AI model

    TypeScript 1

  2. dataset-baymax dataset-baymax Public

    Dataset and AI model used in the "Baymed" project

    Python

  3. tokenizer tokenizer Public

    Tokenizer simples para LLMs, baseado no curso "Building LLMs from sratch", do canal Vizuara

    Jupyter Notebook

  4. subword-tokenizer subword-tokenizer Public

    Tokenizer utilizando vantagens de tokenização por caracteres e por palavras

    Jupyter Notebook

  5. todoTUI todoTUI Public

    To-do list based on terminals for Unix systems

    Python 1

  6. simplified-attention-mechanism simplified-attention-mechanism Public

    Mecanismo de atenção simplificado para LLMs sem a utilização de pesos treináveis

    Jupyter Notebook