Update README.md
Browse files
README.md
CHANGED
|
@@ -31,7 +31,7 @@ Previous releases were based on a SLERP merge of model_stock+della branches focu
|
|
| 31 |
|
| 32 |
A notable contribution from the middle to upper layers of Lamarck v0.6 comes from [Krystalan/DRT-o1-14B](https://huggingface.co/Krystalan/DRT-o1-14B). It has a fascinating research paper: [DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought](https://huggingface.co/papers/2412.17498).
|
| 33 |
|
| 34 |
-
Lamarck 0.6 hit a whole new
|
| 35 |
|
| 36 |
- **Extracted LoRA adapters from special-purpose merges**
|
| 37 |
- **Separate branches for breadcrumbs and DELLA merges**
|
|
|
|
| 31 |
|
| 32 |
A notable contribution from the middle to upper layers of Lamarck v0.6 comes from [Krystalan/DRT-o1-14B](https://huggingface.co/Krystalan/DRT-o1-14B). It has a fascinating research paper: [DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought](https://huggingface.co/papers/2412.17498).
|
| 33 |
|
| 34 |
+
Lamarck 0.6 hit a whole new level of toolchain-automated complexity with its multi-pronged merge strategies:
|
| 35 |
|
| 36 |
- **Extracted LoRA adapters from special-purpose merges**
|
| 37 |
- **Separate branches for breadcrumbs and DELLA merges**
|