Update README.md
Browse files
README.md
CHANGED
|
@@ -24,7 +24,9 @@ entre el conjunto de entrenamiento y el de testeo de 0.9339.
|
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
| 27 |
-
|
|
|
|
|
|
|
| 28 |
|
| 29 |
## Intended uses & limitations
|
| 30 |
|
|
@@ -37,6 +39,9 @@ pregunta-respuesta y contexto.
|
|
| 37 |
|
| 38 |
## Training procedure
|
| 39 |
|
|
|
|
|
|
|
|
|
|
| 40 |
### Training hyperparameters
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
|
|
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
| 27 |
+
Este es un modelo entrenado sobre el modelo original de [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3)
|
| 28 |
+
con el fin de obtner un modelo para un chatbot que responda a preguntas de los casos presentados en la JEP-Colombia. Este
|
| 29 |
+
es un ejercicio académico realizado por estudiantes de la Univalle.
|
| 30 |
|
| 31 |
## Intended uses & limitations
|
| 32 |
|
|
|
|
| 39 |
|
| 40 |
## Training procedure
|
| 41 |
|
| 42 |
+
El modelo fue entrenado por 4 horas con:
|
| 43 |
+
trainable params: 6,815,744 || all params: 7,254,839,296 || trainable%: 0.0939
|
| 44 |
+
|
| 45 |
### Training hyperparameters
|
| 46 |
|
| 47 |
The following hyperparameters were used during training:
|