Commit
•
9071cc0
1
Parent(s):
8e55506
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- davanstrien/haiku_dpo
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
tags:
|
| 8 |
+
- dpo
|
| 9 |
+
- poetry
|
| 10 |
+
base_model:
|
| 11 |
+
- teknium/OpenHermes-2.5-Mistral-7B
|
| 12 |
+
---
|
| 13 |
+
# Model Card for HaikuHermes-0.1-7B
|
| 14 |
+
|
| 15 |
+
This is a very early model which uses the [davanstrien/haiku_dpo](https://huggingface.co/datasets/davanstrien/haiku_dpo) dataset to train [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) using Direct Preference Optimization.
|
| 16 |
+
|
| 17 |
+
The eventual goal of this model is for it to write "technically correct" haiku.
|