Update README.md
Browse files
README.md
CHANGED
|
@@ -12,9 +12,7 @@ tags:
|
|
| 12 |
- dpo
|
| 13 |
- rl
|
| 14 |
datasets:
|
| 15 |
-
-
|
| 16 |
-
- Anthropic/hh-rlhf
|
| 17 |
-
- OpenAssistant/oasst1
|
| 18 |
metrics:
|
| 19 |
- accuracy
|
| 20 |
---
|
|
@@ -30,6 +28,7 @@ To prompt Archangel models, ensure that the format is consistent with that of Tu
|
|
| 30 |
For example, a prompt should be formatted as follows, where `<|user|>` corresponds to the human's role and `<|assistant|>` corresponds to the LLM's role.
|
| 31 |
The human should speak first:
|
| 32 |
```
|
|
|
|
| 33 |
<|user|>
|
| 34 |
Hi! I'm looking for a cake recipe.
|
| 35 |
<|assistant|>
|
|
|
|
| 12 |
- dpo
|
| 13 |
- rl
|
| 14 |
datasets:
|
| 15 |
+
- snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset
|
|
|
|
|
|
|
| 16 |
metrics:
|
| 17 |
- accuracy
|
| 18 |
---
|
|
|
|
| 28 |
For example, a prompt should be formatted as follows, where `<|user|>` corresponds to the human's role and `<|assistant|>` corresponds to the LLM's role.
|
| 29 |
The human should speak first:
|
| 30 |
```
|
| 31 |
+
|
| 32 |
<|user|>
|
| 33 |
Hi! I'm looking for a cake recipe.
|
| 34 |
<|assistant|>
|