Update README.md
Browse files
README.md
CHANGED
|
@@ -3,10 +3,12 @@ pipeline_tag: text-generation
|
|
| 3 |
---
|
| 4 |
Update @ 2024.03.07
|
| 5 |
|
| 6 |
-
Open-platypus-SOLAR-10.7B-v1.0
|
|
|
|
| 7 |
This model is a fine-tuned version of upstage/SOLAR-10.7B-v1.0
|
| 8 |
|
| 9 |
-
Training hyperparameters
|
|
|
|
| 10 |
The following hyperparameters were used during training:
|
| 11 |
|
| 12 |
- batch_size = 16
|
|
@@ -14,7 +16,9 @@ The following hyperparameters were used during training:
|
|
| 14 |
- micro_batch = 1
|
| 15 |
- cutoff_len = 4096
|
| 16 |
- learning_rate = 4e-4
|
| 17 |
-
-
|
|
|
|
|
|
|
| 18 |
- Transformers 4.34.1
|
| 19 |
- Pytorch 2.1.0+cu121
|
| 20 |
- Datasets 2.13.0
|
|
|
|
| 3 |
---
|
| 4 |
Update @ 2024.03.07
|
| 5 |
|
| 6 |
+
## Open-platypus-SOLAR-10.7B-v1.0
|
| 7 |
+
|
| 8 |
This model is a fine-tuned version of upstage/SOLAR-10.7B-v1.0
|
| 9 |
|
| 10 |
+
## Training hyperparameters
|
| 11 |
+
|
| 12 |
The following hyperparameters were used during training:
|
| 13 |
|
| 14 |
- batch_size = 16
|
|
|
|
| 16 |
- micro_batch = 1
|
| 17 |
- cutoff_len = 4096
|
| 18 |
- learning_rate = 4e-4
|
| 19 |
+
-
|
| 20 |
+
## Framework versions
|
| 21 |
+
|
| 22 |
- Transformers 4.34.1
|
| 23 |
- Pytorch 2.1.0+cu121
|
| 24 |
- Datasets 2.13.0
|