Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
| 1 |
This is just a test based on the lora 65b model. Used for the MIT NLP class final project.
|
| 2 |
Then there will be three steps:
|
| 3 |
- Calculate and accumulate gradients
|
|
@@ -16,4 +19,4 @@ python main.py --train_batch_size 8 --valid_batch_size 8 --grad_acc 1 --model_ca
|
|
| 16 |
```
|
| 17 |
---
|
| 18 |
license: mit
|
| 19 |
-
---
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
This is just a test based on the lora 65b model. Used for the MIT NLP class final project.
|
| 5 |
Then there will be three steps:
|
| 6 |
- Calculate and accumulate gradients
|
|
|
|
| 19 |
```
|
| 20 |
---
|
| 21 |
license: mit
|
| 22 |
+
---
|