Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,11 @@ datasets:
|
|
| 10 |
language:
|
| 11 |
- en
|
| 12 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
## Usage
|
| 14 |
|
| 15 |
You can also run this model using the following code:
|
|
|
|
| 10 |
language:
|
| 11 |
- en
|
| 12 |
---
|
| 13 |
+
|
| 14 |
+
# NeuralHermes 2.5 - Mistral 7B
|
| 15 |
+
|
| 16 |
+
NeuralHermes-2.5 was created by fine-tuning OpenHermes-2.5 using a RLHF-like technique: Direct Preference Optimization (DPO) using the `Intel/orca_dpo_pairs` dataset.
|
| 17 |
+
|
| 18 |
## Usage
|
| 19 |
|
| 20 |
You can also run this model using the following code:
|