Update README.md
Browse files
README.md
CHANGED
@@ -44,9 +44,9 @@ For more details, read the paper:
|
|
44 |
|
45 |
| Model | Size | Alignment | GSM8k 8-shot CoT Acc. | AlpacaEval 2 Winrate (LC) |
|
46 |
|-|-|-|-|-|
|
47 |
-
| **Tulu V2.5 PPO 7B (this model)** |
|
48 |
-
| **Tulu V2 DPO 7B** |
|
49 |
-
| **Tulu V2 SFT 7B** |
|
50 |
|
51 |
## Input Format
|
52 |
|
|
|
44 |
|
45 |
| Model | Size | Alignment | GSM8k 8-shot CoT Acc. | AlpacaEval 2 Winrate (LC) |
|
46 |
|-|-|-|-|-|
|
47 |
+
| **Tulu V2.5 PPO 7B (this model)** | 7B | PPO with 7B RM | 38.0 | ? |
|
48 |
+
| **Tulu V2 DPO 7B** | 7B | DPO | 34.5 | 9.3 |
|
49 |
+
| **Tulu V2 SFT 7B** | 7B | - | 34.0 | 7.5 |
|
50 |
|
51 |
## Input Format
|
52 |
|