Mayank Mishra's picture

1644263.7 TFLOPS

Mayank Mishra

mayank-mishra

·

https://mayank31398.github.io/

AI & ML interests

Large Language Models, Distributed Training and Inference

Articles

Improving Hugging Face Training Efficiency Through Packing with Flash Attention

Saving Memory Using Padding-Free Transformer Layers during Finetuning

Aurora-M: The First Open Source Biden-Harris Executive Order Red teamed Multilingual Language Model

Organizations

mayank-mishra's activity

liked a space 3 months ago

Model Release Heatmap

liked a space 5 months ago

FineWeb: decanting the web for the finest text data at scale

liked a dataset 7 months ago

HuggingFaceM4/the_cauldron

Viewer • Updated May 6 • 1.88M • 201k • 331

liked a space 8 months ago

Convert to Safetensors

liked 4 models 8 months ago

bigcode/starcoderbase-7b

Text Generation • Updated Aug 22 • 3.85k • 32

aurora-m/aurora-m-base

Text Generation • Updated Mar 26 • 2.94k • 16

aurora-m/aurora-m-instruct

Text Generation • Updated Mar 12 • 11

aurora-m/aurora-m-biden-harris-redteamed

Text Generation • Updated 1 day ago • 639 • 19