I really, really like watching loss graphs
-
Institut Teknologi Bandung
- Bandung
- zaydzuhri.github.io
- @zmkzmkz
Highlights
- Pro
Block or Report
Block or report zaydzuhri
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned Loading
-
moreformers
moreformers PublicExperimenting on a bunch of transformer variants I come up with. They vary in attention mechanisms, block configurations, etc.
Jupyter Notebook 1
-
pythia-mlkv
pythia-mlkv PublicMulti-Layer Key-Value sharing experiments on Pythia models
-
mlkv
mlkv PublicForked from jquesnelle/yarn
MLKV: Multi-Layer Key-Value Caches for Memory Efficient Transformer Decoding
Python
-
toolongdontread
toolongdontread PublicA text summarizer web app powered by a Flan-T5 model fine-tuned to generate a short TL;DR summary of any text
Jupyter Notebook
-
halubot
halubot PublicHalu is a discord bot that allows you to talk to your favorite (imaginary) characters using the power of AI
Jupyter Notebook
-
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.