Commit
•
d9791fd
1
Parent(s):
d82458f
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
This repo contains a low-rank adapter for LLaMA-7b fit on `Nebulous/gpt4all_pruned`, `sahil2801/CodeAlpaca-20k`, `yahma/alpaca-cleaned` and some datasets part of the OpenAssistant project.
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
This version of the weights was trained with the following hyperparameters:
|
| 9 |
+
|
| 10 |
+
- Epochs: 2
|
| 11 |
+
- Batch size: 128
|
| 12 |
+
- Max Length: 2048
|
| 13 |
+
- Learning rate: 4e-6
|
| 14 |
+
- Lora _r_: 16
|
| 15 |
+
- Lora target modules: q_proj, k_proj, v_proj, o_proj
|
| 16 |
+
|