Saurav Prateek's picture

Saurav Prateek

SauravP97

·

http://sauravp97.github.io/

AI & ML interests

LLM, Deep Neural Nets, Embedding Models

Recent Activity

updated a model 3 days ago

SauravP97/llama-3.2-1B-summarization-loraa-layers

published a model 3 days ago

SauravP97/llama-3.2-1B-summarization-loraa-layers

updated a model 3 days ago

SauravP97/toy-transformer-shakespeare-work

View all activity

Organizations

None yet

Articles 1

Article

1

Visualize the encoding process in HuggingFace Byte-Pair Encoding tokenizer

Papers 2

arxiv:2601.20843

arxiv:2512.03887

models 5

SauravP97/llama-3.2-1B-summarization-loraa-layers

Summarization • Updated 3 days ago

SauravP97/toy-transformer-shakespeare-work

Text Generation • Updated 3 days ago • 120 • 1

SauravP97/tiny-stories-19M-instruct

Text Generation • 19.3M • Updated 18 days ago • 109 • 1

SauravP97/tiny-stories-19M

Text Generation • 19.3M • Updated Feb 18 • 41 • 2

SauravP97/tiny-stories-3M

Text Generation • 3.65M • Updated Feb 5 • 13 • 1

datasets 1

SauravP97/tiny-stories-tokenized-bpe

Viewer • Updated Mar 4 • 2.14M • 32 • 1