Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,6 @@ _The **G**eneral **R**easoning **A**gent (for) **P**roject **E**xploration_
|
|
| 22 |
# Capabilities
|
| 23 |
|
| 24 |
The GRaPE Family was trained on about **14 billion** tokens of data after pre-training. About half was code related tasks, with the rest being heavy on STEAM. Ensuring the model has a sound logical basis.
|
| 25 |
-
> *GRaPE Nano does not have thinking capabilities, primarily in favor of instant responses.*
|
| 26 |
***
|
| 27 |
|
| 28 |
GRaPE Flash and Nano are monomodal models, only accepting text. GRaPE Mini being trained most recently supports image and video inputs.
|
|
@@ -138,4 +137,6 @@ GRaPE 2 will come sooner than the GRaPE 1 family had, and will show multiple imp
|
|
| 138 |
|
| 139 |
There are no benchmarks for GRaPE 1 Models due to the costly nature of running them, as well as prioritization of newer models.
|
| 140 |
|
| 141 |
-
Updates for GRaPE 2 models will be posted here on Huggingface, as well as [Skinnertopia](https://www.skinnertopia.com/)
|
|
|
|
|
|
|
|
|
| 22 |
# Capabilities
|
| 23 |
|
| 24 |
The GRaPE Family was trained on about **14 billion** tokens of data after pre-training. About half was code related tasks, with the rest being heavy on STEAM. Ensuring the model has a sound logical basis.
|
|
|
|
| 25 |
***
|
| 26 |
|
| 27 |
GRaPE Flash and Nano are monomodal models, only accepting text. GRaPE Mini being trained most recently supports image and video inputs.
|
|
|
|
| 137 |
|
| 138 |
There are no benchmarks for GRaPE 1 Models due to the costly nature of running them, as well as prioritization of newer models.
|
| 139 |
|
| 140 |
+
Updates for GRaPE 2 models will be posted here on Huggingface, as well as [Skinnertopia](https://www.skinnertopia.com/)
|
| 141 |
+
|
| 142 |
+
Demos for select GRaPE Models can be found here: https://github.com/Sweaterdog/GRaPE-Demos
|