🤖
Training some models
AI researcher addicted to dungeons and dragons.
Research fellow @ KAUST
-
KAUST (King Abdullah University of Science & Technology)
- Saudi Arabia
-
14:24
(UTC +03:00) - in/sulrash
Highlights
- Pro
Pinned Loading
-
minLLMTrain
minLLMTrain PublicMinimal yet high performant code for pretraining llms. Attempts to implement some SOTA features. Implements training through: Deepspeed, Megatron-LM, and FSDP. WIP
Python 5
-
Cheatsheet
Cheatsheet PublicAn attempt at improving facial recognition performance through appending a 'cheatsheet' to an image with one positive sample and multiple negatives during training.
Python 5
-
Graduation-Project
Graduation-Project PublicMy final year honours project that involved developing a rogue like game from scratch and implementing some RL algorithms. The purpose was to compare perfect information vs imperfect information. I…
Python 1
-
AnshulSood11/Engagement-Level-Prediction
AnshulSood11/Engagement-Level-Prediction PublicEngagement Intensity Prediction in Real TIme
-
microsoft/Megatron-DeepSpeed
microsoft/Megatron-DeepSpeed PublicForked from NVIDIA/Megatron-LM
Ongoing research training transformer language models at scale, including: BERT & GPT-2
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.