Skip to content
View JohnGiorgi's full-sized avatar

Highlights

  • Pro

Organizations

@bowang-lab

Block or report JohnGiorgi

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
JohnGiorgi/README.md

Hi there 👋

Twitter GitHub Linkedin

I am ML research scientist at Abridge working on training language models that aid and assist doctors in various clinical documentation tasks. I obtained a computer science Ph.D. at the University of Toronto and was a graduate student researcher at the Donnelly Centre for Cellular and Biomolecular Research and the Vector Institute for Artificial Intelligence, were my work centred on natural language processing (NLP) and natural language understanding (NLU) of scientific text, particularly biomedical literature. I previously interned at Ai2 (on the Semantic Scholar team) and at Semantic Health. I completed an undergraduate degree at the University of Ottawa, graduating with a B.Sc in biochemistry. I completed an M.Sc. in computer science at the University of Toronto. When I am not 💻 I like to 🚵‍♂️, 🏂 and 🏋️‍♂️.

Pinned Loading

  1. DeCLUTR Public

    The corresponding code from our paper "DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations". Do not hesitate to open an issue if you run into any trouble!

    Python 381 33

  2. seq2rel Public

    The corresponding code for our paper: A sequence-to-sequence approach for document-level relation extraction.

    Jupyter Notebook 63 8

  3. allenai/open-mds Public

    The corresponding code for our paper: "Exploring the Challenges of Open Domain Multi-Document Summarization". Do not hesitate to open an issue if you run into any trouble!

    Python 32 1

  4. BaderLab/Transfer-Learning-BNER-Bioinformatics-2018 Public

    This repository contains supplementary data, and links to the model and corpora used for the paper: Transfer learning for biomedical named entity recognition with neural networks.

    Python 37 6

  5. PathwayCommons/semantic-search Public

    A simple semantic search engine for scientific papers.

    Python 28

  6. mathematics-for-machine-learning Public

    A set of notes, in the form of a simple Github Pages site, which will serve as a complete crash course on the various areas of mathematics essential to understanding machine learning.

    Jupyter Notebook 63 21

493 contributions in the last year

Contribution Graph
Day of Week February March April May June July August September October November December January February
Sunday
Monday
Tuesday
Wednesday
Thursday
Friday
Saturday
Less
No contributions.
Low contributions.
Medium-low contributions.
Medium-high contributions.
High contributions.
More

Activity overview

Contributed to allenai/TOPICAL, huggingface/trl, vllm-project/vllm and 11 other repositories
Loading A graph representing JohnGiorgi's contributions from February 11, 2024 to February 16, 2025. The contributions are 72% commits, 13% code review, 11% pull requests, 4% issues.

Contribution activity

February 2025

Created 1 repository

Created a pull request in huggingface/trl that received 2 comments

Raise UserWarning in RewardTraining if PEFT target_modules="all-linear"

What does this PR do? I ran into a nasty edge case that I don't think is documented anywhere when using the RewardTrainer to train a reward model. …

+36 −0 lines changed 2 comments
Opened 1 other pull request in 1 repository
huggingface/evaluate 1 open
Reviewed 2 pull requests in 2 repositories
huggingface/evaluate 1 pull request
huggingface/trl 1 pull request

Created an issue in huggingface/trl that received 1 comment

Llama 3 family of models does not seem to work with RewardTrainer

Reproduction I noticed, when trying to train Llama3.1-8B with the RewardTrainer for my own problem, that seemingly no matter what I tried I couldn'…

5 tasks done
1 comment
92 contributions in private repositories Feb 1 – Feb 15
Loading

Seeing something unexpected? Take a look at the GitHub profile guide.