A LLM trained only on data from certain time periods to reduce modern bias
Python
Revise README with language options and project info
Hayk Grigorian2ca1d367c22f
diff --git a/README.md b/README.mdindex 15c33aa..e79a132 100644--- a/README.md+++ b/README.md@@ -182,22 +182,27 @@ v2mini-eval2: 200M Parametersv2: 1.2B Parameters-# Training Specs ?+## Training Specs ?-# v0/v0.5+### v0/v0.5GPU: Geforce rtx 4060CPU: i5-13400FRam: 16GB DDR5.-# v1+### v1GPU: A100 SXM rented-# v2mini-eval1/eval2+### v2mini-eval1/eval2GPU: A100 SXM rented-# v2+### v2GPU: H100 SXM rented+## Acknowledgements++I would like to thank [Dr. Hamed Yaghoobian](https://hamedyaghoobian.com) for academic supervision, guidance on research framing and evaluation, and for assistance with tokenizer training and dataset preparation for the v2 release. His feedback and experience were instrumental in refining the presentation of this work.++