Commit
•
7be8b25
1
Parent(s):
c5a510c
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,9 @@ pipeline_tag: text-generation
|
|
| 10 |
|
| 11 |
# phi-2-alpaca-cleaned
|
| 12 |
This model is an instruction-tuned version of the [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) model fine-tuned on the [yahma/alpaca-cleaned](https://huggingface.co/datasets/yahma/alpaca-cleaned) dataset.
|
|
|
|
| 13 |
In the training, full parameter fine-tuning of phi-2 was performed, and LoRA was not used.
|
|
|
|
| 14 |
## Training
|
| 15 |
- GPUs: 8 × A6000 48GB
|
| 16 |
- per_device_train_batch_size 8
|
|
|
|
| 10 |
|
| 11 |
# phi-2-alpaca-cleaned
|
| 12 |
This model is an instruction-tuned version of the [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) model fine-tuned on the [yahma/alpaca-cleaned](https://huggingface.co/datasets/yahma/alpaca-cleaned) dataset.
|
| 13 |
+
|
| 14 |
In the training, full parameter fine-tuning of phi-2 was performed, and LoRA was not used.
|
| 15 |
+
|
| 16 |
## Training
|
| 17 |
- GPUs: 8 × A6000 48GB
|
| 18 |
- per_device_train_batch_size 8
|