picoLLM

classroom

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

aditeyabaral authored a paper about 1 month ago

Closing the Calibration Gap in Semantic Caching

aditeyabaral authored a paper about 1 month ago

Training for Compositional Sensitivity Reduces Dense Retrieval Generalization

aditeyabaral authored a paper about 1 month ago

Can LLMs $\textit{understand}$ Math? -- Exploring the Pitfalls in Mathematical Reasoning

View all activity

models 27

pico-llm/transformer-small-1M-embed384-heads6-blocks6-prenorm-posabs-epochs5

49.3M • Updated Nov 20, 2025 • 16

pico-llm/transformer-tiny-1M-embed128-heads2-blocks2-prenorm-posabs-epochs5

13.3M • Updated Nov 20, 2025 • 18

pico-llm/transformer-pico-1M-embed64-heads1-blocks1-postnorm-posnone-epochs5

6.48M • Updated Nov 20, 2025 • 1

pico-llm/gpt2-base-postnorm-absolute

0.2B • Updated Nov 18, 2025 • 4

pico-llm/kgram-pico-K1-L1-scaled

3.27M • Updated Nov 18, 2025 • 2

pico-llm/kgram-pico-K3-L1-scaled

2.16M • Updated Nov 18, 2025 • 14

pico-llm/kgram-small-K5-L5-onehot

77.6M • Updated Nov 18, 2025 • 7

pico-llm/kgram-tiny-K5-L3-onehot

19.4M • Updated Nov 18, 2025 • 3

pico-llm/kgram-small-K5-L5-scaled

15.9M • Updated Nov 18, 2025 • 4

pico-llm/kgram-tiny-K5-L3-scaled

3.89M • Updated Nov 18, 2025 • 3

datasets 0

None public yet