Update README.md
Browse files
README.md
CHANGED
|
@@ -2,4 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model:
|
| 4 |
- Qwen/Qwen2.5-14B
|
| 5 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model:
|
| 4 |
- Qwen/Qwen2.5-14B
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
Trained the eos_token into the lm_head.
|
| 8 |
+
|
| 9 |
+
This should allow qlora finetunes with 24 or even 16 GB of vram.
|