Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,6 @@ inference: false
|
|
| 5 |
|
| 6 |
# Info
|
| 7 |
|
| 8 |
-
This is the model [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) which I cut
|
| 9 |
|
| 10 |
It's necessary to pre-train this model, cause at the moment is generating just gibberish.
|
|
|
|
| 5 |
|
| 6 |
# Info
|
| 7 |
|
| 8 |
+
This is the model [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) which I cut all the intermediate(feed_forward_length) size with 14336 down to 3072, resulting in a ~2.81B model.
|
| 9 |
|
| 10 |
It's necessary to pre-train this model, cause at the moment is generating just gibberish.
|