Commit
•
6d2faf0
1
Parent(s):
f1c8a6f
Update README.md
Browse files
README.md
CHANGED
|
@@ -77,12 +77,13 @@ Use the code below to get started with the model.
|
|
| 77 |
|
| 78 |
### Training Data
|
| 79 |
|
|
|
|
| 80 |
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
|
| 82 |
[More Information Needed]
|
| 83 |
|
| 84 |
### Training Procedure
|
| 85 |
-
|
| 86 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
|
| 88 |
#### Preprocessing [optional]
|
|
|
|
| 77 |
|
| 78 |
### Training Data
|
| 79 |
|
| 80 |
+
This iteration of Microsof Phi 2 is trained on the kaggle dataset by ruslanmv [ai-medical-chatbot](https://huggingface.co/datasets/ruslanmv/ai-medical-chatbot)
|
| 81 |
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 82 |
|
| 83 |
[More Information Needed]
|
| 84 |
|
| 85 |
### Training Procedure
|
| 86 |
+
This model has been simply finetuned leveraging [wandb](https://wandb.ai/home) and [LoRa](https://arxiv.org/abs/2106.09685)
|
| 87 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 88 |
|
| 89 |
#### Preprocessing [optional]
|