tomeras1 commited on
Commit
83cec42
1 Parent(s): 7a01e39

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -7,4 +7,4 @@ This is a tiny Jamba model used for development, debugging and experimentation o
7
  It has 319M parameters (instead of 52B in [Jamba 1.5 Mini](https://huggingface.co/ai21labs/AI21-Jamba-1.5-Mini) (and [Jamba v0.1](https://huggingface.co/ai21labs/Jamba-v0.1)) and 398B in [Jamba 1.5 Large](https://huggingface.co/ai21labs/AI21-Jamba-1.5-Large)),
8
  and was trained on ~40B tokens.
9
 
10
- It is great for use in unittests since it is a small model (doesn't take long to download) thas has valid and non-random outputs. Yet, **it did not undergo extensive training and should not be expected to generate high-quality text**.
 
7
  It has 319M parameters (instead of 52B in [Jamba 1.5 Mini](https://huggingface.co/ai21labs/AI21-Jamba-1.5-Mini) (and [Jamba v0.1](https://huggingface.co/ai21labs/Jamba-v0.1)) and 398B in [Jamba 1.5 Large](https://huggingface.co/ai21labs/AI21-Jamba-1.5-Large)),
8
  and was trained on ~40B tokens.
9
 
10
+ It is great for use in unittests since it is a small model (doesn't take long to download) that has valid and non-random outputs. Yet, **it did not undergo extensive training and should not be expected to generate high-quality text**.