mbalesni Goto Github PK

accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

ai-safety-paper-notes

Summaries, notes and questions on AI safety research papers.

allenai

anthropic-hack-23

arena_2.0

Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.

big-bench-hard

Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

calib_challenge

The comma.ai Calibration Challenge!

censored-cognition

clock-sync-golang

color-palette

An interactive color palette.

covid-mirna

Does COVID do this nasty thing?

deep-learning-paper-notes

Summaries, notes, questions on Deep Learning research papers.

deepspeed_llama

Finetuning LLaMA with DeepSpeed

deeptraffic

Deep Learning models for network traffic classification

diia-integration

dtw

Comparing trading algos accuracy&profitability using various distance metrics (Dynamic Time Warp, Time Warp Edit Distance, Longest Common Subsequence, Correlation)

ebm-driving

efficientzero

Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

g-in-llms

gestures-training-ui

A Processing sketch that implements UI for a gestures training application

gpt-honest-articulation

Exploring GPT-3 ability to articulate its knowledge

grok

ibc

(Fork of) Official implementation of Implicit Behavioral Cloning, as described in our CoRL 2021 paper, see more at https://implicitbc.github.io/

iphone-checker

llm-security-challenge

Can Large Language Models Solve Security Challenges? We test LLMs' ability to interact and break out of shell environments using the OverTheWire wargames environment, showing the models' surprising ability to do action-oriented cyberexploits in shell environments

malware-labeler

mats-3-aligning-lms

A common repo of the MATS 3.0 stream on Aligning Language Models

mbalesni.github.io

next-js-with-passport

node-rsa-nopadding

A boilerplate for `node-rsa` package encryption/decryption without padding