Update README.md
Browse files
README.md
CHANGED
|
@@ -104,11 +104,11 @@ Target Modules
|
|
| 104 |
▼
|
| 105 |
Selects which modules to target in training. Targeting more modules is closer to a full fine-tune at the cost of increased VRAM requirements and adapter size. NOTE: Only works for model_id='llama', other types will retain default training behavior and not use these settings.
|
| 106 |
|
| 107 |
-
Enable q_proj
|
| 108 |
-
Enable v_proj
|
| 109 |
-
Enable k_proj
|
| 110 |
-
Enable o_proj
|
| 111 |
-
Enable gate_proj
|
| 112 |
-
Enable down_proj
|
| 113 |
-
Enable up_proj
|
| 114 |
|
|
|
|
| 104 |
▼
|
| 105 |
Selects which modules to target in training. Targeting more modules is closer to a full fine-tune at the cost of increased VRAM requirements and adapter size. NOTE: Only works for model_id='llama', other types will retain default training behavior and not use these settings.
|
| 106 |
|
| 107 |
+
- Enable q_proj
|
| 108 |
+
- Enable v_proj
|
| 109 |
+
- Enable k_proj
|
| 110 |
+
- Enable o_proj
|
| 111 |
+
- Enable gate_proj
|
| 112 |
+
- Enable down_proj
|
| 113 |
+
- Enable up_proj
|
| 114 |
|