Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
jwan584
on Sept 22, 2023
|
parent
|
context
|
favorite
| on:
BTLM-3B-8K: 7B Parameter Performance in a 3B Param...
A helpful paper with the full recipe Cerebras uses to train LLMs and their process including: - Extensively deduplicated dataset (SlimPajama) - Hyperparameter search using muP - Variable sequence length training + ALiBi - Aggressive LR decay
Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
