Harley-ml commited on
Commit
76e6988
·
verified ·
1 Parent(s): dbc71ae

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -23,7 +23,7 @@ tags:
23
 
24
  # Tiny-Word
25
 
26
- Tiny-Word is an extremely tiny Mistral-like model, approximately ~81k parameters. It generates English or Spanish words or word-like sequences.
27
 
28
  ## Architecture
29
 
@@ -78,7 +78,7 @@ Tiny-Word was trained on Google Colaboratory, with 1 Nvidia Tesla T4 GPU, 15 GB
78
  | 12000 | 3.5139 | 3.5161 | ~33.6 | ~33.7 |
79
  | 15000 | 3.4784 | 3.4861 | ~32.4 | ~32.6 |
80
 
81
- Tiny-Word shows promising results, even at its tiny size (~81k parameters). Given the relatively easy task (predicting subwords inside single words), this is expected.
82
 
83
  ## Generation Examples
84
 
 
23
 
24
  # Tiny-Word
25
 
26
+ Tiny-Word is an extremely tiny Mistral-like model, approximately ~134k parameters. It generates English or Spanish words or word-like sequences.
27
 
28
  ## Architecture
29
 
 
78
  | 12000 | 3.5139 | 3.5161 | ~33.6 | ~33.7 |
79
  | 15000 | 3.4784 | 3.4861 | ~32.4 | ~32.6 |
80
 
81
+ Tiny-Word shows promising results, even at its tiny size (~134k parameters). Given the relatively easy task (predicting subwords inside single words), this is expected.
82
 
83
  ## Generation Examples
84