Update README.md
Browse files
README.md
CHANGED
|
@@ -24,9 +24,12 @@ pipeline_tag: text-generation
|
|
| 24 |
This model was trained with a superset of 200,000 instructions in Portuguese.
|
| 25 |
The model comes to help fill the gap in models in Portuguese. Tuned from the Mistral 7b in Portuguese, the model was adjusted mainly for instructional tasks.
|
| 26 |
|
| 27 |
-
|
| 28 |
# How to use
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
You can use the model in its normal form up to 4-bit quantization. Below we will use both approaches.
|
| 31 |
Remember that verbs are important in your prompt. Tell your model how to act or behave so that you can guide them along the path of their response.
|
| 32 |
Important points like these help models (even smaller models like 7b) to perform much better.
|
|
|
|
| 24 |
This model was trained with a superset of 200,000 instructions in Portuguese.
|
| 25 |
The model comes to help fill the gap in models in Portuguese. Tuned from the Mistral 7b in Portuguese, the model was adjusted mainly for instructional tasks.
|
| 26 |
|
|
|
|
| 27 |
# How to use
|
| 28 |
|
| 29 |
+
### FULL MODEL : A100
|
| 30 |
+
### HALF MODEL: L4
|
| 31 |
+
### 8bit or 4bit : T4 or V100
|
| 32 |
+
|
| 33 |
You can use the model in its normal form up to 4-bit quantization. Below we will use both approaches.
|
| 34 |
Remember that verbs are important in your prompt. Tell your model how to act or behave so that you can guide them along the path of their response.
|
| 35 |
Important points like these help models (even smaller models like 7b) to perform much better.
|