SulRash/nanoagent
Just me learning and cooking something
Research engineer @AdaMLLab at KAUST
Repositories
SulRash/modded-nanot5
Learning how to make transformers go faster
SulRash/Stable-Retro
A fork of gym-retro with additional games, emulators and supported platforms
SulRash/EasyRogue-2
EasyRogue reincarnated better!
SulRash/EasyRogue
A simple rogue like game ripped out from my third year project titled "Perfect Information Versus Imperfect Information in Reinforcement Learning". I had made this simple game to benchmark performance, and I hope other people can get some use out of it too!
SulRash/nanochat
The best ChatGPT that $100 can buy.
SulRash/SulRash
SulRash/modded-nanogpt
NanoGPT (124M) in 2 minutes
SulRash/nanotron
Minimalistic large language model 3D-parallelism training
SulRash/huggingface-text-data-analyzer
Analyzes text datasets from huggingface for training LLMs!
SulRash/MonteCarlo-Hex
AI and Games project
SulRash/captum
fixing bug with some LLMs that don't generate bos
SulRash/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
SulRash/lighteval
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
SulRash/pystk
For RL course students who want to run this on their macbook
SulRash/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
SulRash/open-instruct
SulRash/NeMo-Aligner
Scalable toolkit for efficient model alignment
SulRash/Qwen2-VL
Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
SulRash/envenc
Repository for environment encoder, an attempt at improving reinforcement learning agents' generalisability through learning how to act on universal multimodal embeddings generated by a vision-language model.
SulRash/Cheatsheet
An attempt at improving facial recognition performance through appending a 'cheatsheet' to an image with one positive sample and multiple negatives during training.
SulRash/python-pathfinding
Implementation of common pathfinding algorithms. My fork just adds naive random walks.
SulRash/ntaGPT
A fork of nanoGPT for my project NTA
SulRash/MedievalSD
Just a quick little project I'm working on for my dungeons & dragons world, creating a stable diffusion model that can reliably create those medieval sketch drawings. Most probably will LoRA it.
SulRash/minLLMTrain
Minimal yet high performant code for pretraining llms. Attempts to implement some SOTA features. Implements training through: Deepspeed, Megatron-LM, and FSDP. WIP
SulRash/datatrove
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
SulRash/SAPIEN
SulRash/inseq
Interpretability for sequence generation models 🐛 🔍
SulRash/Engagement-Level-Prediction
Engagement Intensity Prediction in Real TIme (converted to tf2)
SulRash/lm-evaluation-harness
Fork of LM harness to add attention mapping