Update README.md
Browse files
README.md
CHANGED
|
@@ -9,10 +9,13 @@ datasets:
|
|
| 9 |
- jondurbin/bagel-v0.3
|
| 10 |
library_name: transformers
|
| 11 |
---
|
| 12 |
-
|
|
|
|
| 13 |
# UNA-TheBeagle-7b-v1
|
| 14 |
TheBeagle, a model of 7B parameters trained on The Bagel dataset. DPO & UNA applied over a set of curated DPO Pairs.
|
| 15 |
|
|
|
|
|
|
|
| 16 |
The dataset was generated using the original bagel code, including the decontamination step.
|
| 17 |
|
| 18 |
As base model, we used the latest Intel's neural-chat model.
|
|
|
|
| 9 |
- jondurbin/bagel-v0.3
|
| 10 |
library_name: transformers
|
| 11 |
---
|
| 12 |
+
-- In the Love Memory of my "LoLa" --
|
| 13 |
+
|
| 14 |
# UNA-TheBeagle-7b-v1
|
| 15 |
TheBeagle, a model of 7B parameters trained on The Bagel dataset. DPO & UNA applied over a set of curated DPO Pairs.
|
| 16 |
|
| 17 |
+
- Scored #1 on the HF Leaderboard, dramatic scores!!! 73 ARC, and very well balanced!
|
| 18 |
+
|
| 19 |
The dataset was generated using the original bagel code, including the decontamination step.
|
| 20 |
|
| 21 |
As base model, we used the latest Intel's neural-chat model.
|