updated readme
Browse files
README.md
CHANGED
|
@@ -1,3 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
---
|
|
|
|
| 1 |
+
<table>
|
| 2 |
+
<tr>
|
| 3 |
+
<td style="width: 30%; text-align: center; vertical-align: middle">
|
| 4 |
+
|
| 5 |
+
# CurtGPT
|
| 6 |
+
Using Microsoft's Phi 1.5 model like it was never intended.
|
| 7 |
+
|
| 8 |
+
</td>
|
| 9 |
+
<td style="text-align: center;">
|
| 10 |
+
<img src="https://github.com/tim-a-davis/silly_little_language_modeling_thing_at_utd/blob/main/curtgpt%20logo.png?raw=true" width="300" height="auto">
|
| 11 |
+
</td>
|
| 12 |
+
</tr>
|
| 13 |
+
</table>
|
| 14 |
+
|
| 15 |
+
# Main Procedure
|
| 16 |
+
This model is an adapter on [puffin phi v2](https://huggingface.co/teknium/Puffin-Phi-v2) trained using QLoRA and DPO on 60,000 samples from the [anthropic helpful only](https://huggingface.co/datasets/pvduy/rm_hh_helpful_only) dataset.
|
| 17 |
+
|
| 18 |
+
|
| 19 |
---
|
| 20 |
library_name: peft
|
| 21 |
---
|