Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- rxavier/economicus
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
tags:
|
| 8 |
+
- chatml
|
| 9 |
+
- mistral
|
| 10 |
+
- instruct
|
| 11 |
+
- openhermes
|
| 12 |
+
- economics
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# Taurus 1.0
|
| 16 |
+
|
| 17 |
+
## Description
|
| 18 |
+
|
| 19 |
+
Taurus is an [OpenHermes 2.5](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) finetune using the [Economicus dataset](https://huggingface.co/datasets/rxavier/economicus), an instruct dataset synthetically generated from Economics PhD textbooks.
|
| 20 |
+
|
| 21 |
+
The model was trained for 2 epochs (QLoRA) using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl). The exact config I used can be found [here](https://huggingface.co/rxavier/Taurus-1.0-Mistral-7B/tree/main/axolotl).
|
| 22 |
+
|
| 23 |
+
## Prompt format
|
| 24 |
+
|
| 25 |
+
Taurus uses **ChatML**.
|
| 26 |
+
|
| 27 |
+
```
|
| 28 |
+
<|im_start|>system
|
| 29 |
+
System message
|
| 30 |
+
<|im_start|>user
|
| 31 |
+
User message<|im_end|>
|
| 32 |
+
<|im_start|>assistant
|
| 33 |
+
```
|