A LLM trained only on data from certain time periods to reduce modern bias
Python
Revise README with language options and model details
Hayk Grigorian58539739a1d2
diff --git a/README.md b/README.mdindex 33acc36..48efec9 100644--- a/README.md+++ b/README.md@@ -122,9 +122,10 @@ I'm using books, legal documents, newspapers, and other writings from 1800–187https://github.com/haykgrigo3/TimeCapsuleLLM/blob/main/Copy%20of%20London%20Documents%20for%20Time%20Capsule%20LLM.txtDataset sizes:-v0: ~187MB-v0.5: ~435MB-v1: ~6.25GB+- v0: ~187MB+- v0.5: ~435MB+- v1: ~6.25GB+- v2mini-eval1: 15GB## How large are the models ?@@ -134,7 +135,7 @@ v0.5 123M Parametersv1: 700M Parameters-v2:+v2mini-eval1: 300M Parameters# Training Specs ?@@ -144,9 +145,12 @@ CPU: i5-13400FRam: 16GB DDR5.# v1-GPU: A100 rented+GPU: A100 SXM rented++# v2mini-eval1++GPU: A100 SXM rented-# v2