Update README.md
Browse files
README.md
CHANGED
|
@@ -48,10 +48,23 @@ pipeline_tag: text-generation
|
|
| 48 |
- [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only)
|
| 49 |
- [GAIR/lima](https://huggingface.co/datasets/GAIR/lima)
|
| 50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
## Hardware and Software
|
| 52 |
|
| 53 |
### Hardware
|
| 54 |
-
- We utilized an
|
| 55 |
|
| 56 |
### Training Factors
|
| 57 |
- We fine-tuned this model using a combination of the [DeepSpeed library](https://github.com/microsoft/DeepSpeed) and the [HuggingFace trainer](https://huggingface.co/docs/transformers/main_classes/trainer).
|
|
|
|
| 48 |
- [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only)
|
| 49 |
- [GAIR/lima](https://huggingface.co/datasets/GAIR/lima)
|
| 50 |
|
| 51 |
+
### Prompt Template
|
| 52 |
+
```
|
| 53 |
+
### System:
|
| 54 |
+
{System}
|
| 55 |
+
|
| 56 |
+
### User:
|
| 57 |
+
{User}
|
| 58 |
+
|
| 59 |
+
### Assistant:
|
| 60 |
+
{Assistant}
|
| 61 |
+
```
|
| 62 |
+
|
| 63 |
+
|
| 64 |
## Hardware and Software
|
| 65 |
|
| 66 |
### Hardware
|
| 67 |
+
- We utilized an A100x8 for training our model.
|
| 68 |
|
| 69 |
### Training Factors
|
| 70 |
- We fine-tuned this model using a combination of the [DeepSpeed library](https://github.com/microsoft/DeepSpeed) and the [HuggingFace trainer](https://huggingface.co/docs/transformers/main_classes/trainer).
|