crumb
/

gpt2023

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

crumb commited on Apr 30, 2023

Commit

6c94017

•

1 Parent(s): 89fea6a

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -3,7 +3,7 @@ license: mit
 language:
 - en
 ---
-The smallest GPT-2 finetuned on approximately 2.23B tokens (almost the 24.8B needed to 'chinchilla-optimally' pretrain it!) consisting of 1.3B from common crawl sites from 2023, 540M from ArXiv, and 390M from GitHub.
 *(from GPT-2 model card)*

 language:
 - en
 ---
+The smallest GPT-2 finetuned on approximately 2.23B tokens (almost the 2.48B needed to 'chinchilla-optimally' pretrain it!) consisting of 1.3B from common crawl sites from 2023, 540M from ArXiv, and 390M from GitHub.
 *(from GPT-2 model card)*