Keynote-Technology
/

TinyKAI-0.7B-v0.1

Text Generation

text-generation-inference

Model card Files Files and versions

PlanetDOGE commited on Nov 15, 2023

Commit

e20b847

·

1 Parent(s): 3e76622

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ datasets:
 ## Model Details
 TinyKAI-0.7B is one of the world's SMALLEST "large" language models EVER!
-We acheived such a feat by essentially compressing [GPT2](https://huggingface.co/gpt2) and squeezing it to be UNDER 1 billion parameters!
 ## Uses
 Due to being one of the tiniest "large" language models on huggingface, many corners had to be cut. TinyKAI-0.7B has a max output of only 150 characters per computation (without repeating itself). Therefore, TinyKAI is only intended for research purposes.

 ## Model Details
 TinyKAI-0.7B is one of the world's SMALLEST "large" language models EVER!
+We acheived such a feat by essentially compressing [GPT2](https://huggingface.co/gpt2) and squeezing it to fit into one sub-GB pytorch.bin file!
 ## Uses
 Due to being one of the tiniest "large" language models on huggingface, many corners had to be cut. TinyKAI-0.7B has a max output of only 150 characters per computation (without repeating itself). Therefore, TinyKAI is only intended for research purposes.