Commit
•
1ed66f8
1
Parent(s):
9dd1412
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,12 +13,13 @@ The model structure is from [phi-1.5](https://huggingface.co/microsoft/phi-1_5),
|
|
| 13 |
|
| 14 |
It was trained on a small subset of the [wikipedia dataset](https://huggingface.co/datasets/wikipedia) dataset, for research validation purpose only.
|
| 15 |
|
| 16 |
-
Please notice the kernel is not optimzed for 1-bit matrix yet.
|
| 17 |
|
| 18 |
```python
|
| 19 |
dataset = load_dataset("wikipedia", "20220301.en")
|
| 20 |
dataset = dataset['train'].select(range(int(1e5)))
|
| 21 |
```
|
|
|
|
|
|
|
| 22 |
The model is trained on a 3090(24GB) for 16 hours.
|
| 23 |
|
| 24 |
### For training code, check --placeholder--.
|
|
|
|
| 13 |
|
| 14 |
It was trained on a small subset of the [wikipedia dataset](https://huggingface.co/datasets/wikipedia) dataset, for research validation purpose only.
|
| 15 |
|
|
|
|
| 16 |
|
| 17 |
```python
|
| 18 |
dataset = load_dataset("wikipedia", "20220301.en")
|
| 19 |
dataset = dataset['train'].select(range(int(1e5)))
|
| 20 |
```
|
| 21 |
+
Please notice the kernel is not optimzed for 1-bit matrix yet.
|
| 22 |
+
|
| 23 |
The model is trained on a 3090(24GB) for 16 hours.
|
| 24 |
|
| 25 |
### For training code, check --placeholder--.
|