Commit
•
9ff390a
1
Parent(s):
53e5b63
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,8 @@ tags:
|
|
| 6 |
- lazymergekit
|
| 7 |
- mlabonne/NeuralBeagle14-7B
|
| 8 |
- mlabonne/NeuralDaredevil-7B
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
# DareBeagle-7B
|
|
@@ -16,7 +18,7 @@ DareBeagle-7B is a merge of the following models using [LazyMergekit](https://co
|
|
| 16 |
|
| 17 |
As an experiment to find the best base merge to further fine-tuning, expect a lot of experiments named using parts of the component models until a clear winner emerges in the benchmarks
|
| 18 |
|
| 19 |
-
In this case
|
| 20 |
|
| 21 |
## 🧩 Configuration
|
| 22 |
|
|
|
|
| 6 |
- lazymergekit
|
| 7 |
- mlabonne/NeuralBeagle14-7B
|
| 8 |
- mlabonne/NeuralDaredevil-7B
|
| 9 |
+
datasets:
|
| 10 |
+
- argilla/distilabel-intel-orca-dpo-pairs
|
| 11 |
---
|
| 12 |
|
| 13 |
# DareBeagle-7B
|
|
|
|
| 18 |
|
| 19 |
As an experiment to find the best base merge to further fine-tuning, expect a lot of experiments named using parts of the component models until a clear winner emerges in the benchmarks
|
| 20 |
|
| 21 |
+
In this case merging the DPO versions of 2 merge models with different characterisics to meassure what capabilities remain or improve
|
| 22 |
|
| 23 |
## 🧩 Configuration
|
| 24 |
|