Anothet intermediate version as I continue to experiment with DPO. This one feels usable but has some formatting issues. working on cleaning the DPO data.

An experimental llama3 RP model, stuffed with lots of tokens and then DPO'd for RP. Making it public so people can give me feedback and mess around with it.

Uses ChatML but you have to format it a certain way. The usernames are required, a system prompt is required.

Datasets Used?

Yes.

Prompt Format ( ChatML with usernames. )

<|im_start|>system
{System Prompt}<|im_end|>
<|im_start|>user
{username}: {usertext}<|im_end|>
<|im_start|>assistant
{botname}: {bottext}<|im_end|>
<|im_start|>user
{username}: {usertext}<|im_end|>
<|im_start|>assistant
{botname}:

Disclaimer

Please prompt responsibly and take anything outputted by any Language Model with a huge grain of salt. Thanks!