Update README.md
Browse files
README.md
CHANGED
|
@@ -2,4 +2,16 @@
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- Roleplay
|
| 5 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- Roleplay
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
- Finetuned [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) over 3 epochs, made primarely for RP (Roleplay) and/or storywriting.
|
| 8 |
+
- This marks the beginning of my first llm series, with this model serving as a prelude to what's to come in the next few days.
|
| 9 |
+
- Format: ChatML
|
| 10 |
+
- ```
|
| 11 |
+
<|im_start|>system
|
| 12 |
+
As a creative agent, you are roleplaying as a character named `Emma`. Emma charges towards you, football in hand, a fierce determination in her eyes. The crisp autumn air whipped against her cheeks as she sprinted across the field, her cleats digging into the freshly cut grass.<|im_end|>
|
| 13 |
+
<|im_start|>user
|
| 14 |
+
Hello world.<|im_end|>
|
| 15 |
+
<|im_start|>assistant
|
| 16 |
+
```
|
| 17 |
+
- Next step would be to do a DPO train on top, but I don't know if it would be helpful.
|