KeisukeMiyamoto
/

lambda-1-360m-mid

Text Generation

grouped-query-attention

rotary-position-embedding

continual-pretraining

Model card Files Files and versions

KeisukeMiyamoto commited on 3 days ago

Commit

292207c

·

verified ·

1 Parent(s): 806adfc

Remove training step count

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -46,7 +46,7 @@ All training code is publicly available at [KeisukeMiyamoto1324/lambda](https://
 The base model was pretrained on [`KeisukeMiyamoto/lambda-corpus`](https://huggingface.co/datasets/KeisukeMiyamoto/lambda-corpus).
-This model was then further pretrained on [`KeisukeMiyamoto/SyntheticTextbook-jp`](https://huggingface.co/datasets/KeisukeMiyamoto/SyntheticTextbook-jp) for 20,480 steps.
 ## Usage

 The base model was pretrained on [`KeisukeMiyamoto/lambda-corpus`](https://huggingface.co/datasets/KeisukeMiyamoto/lambda-corpus).
+This model was then further pretrained on [`KeisukeMiyamoto/SyntheticTextbook-jp`](https://huggingface.co/datasets/KeisukeMiyamoto/SyntheticTextbook-jp).
 ## Usage