A sequel! A sequel to my Francois-PE/Huali train, Built ontop of Dans-PE-12B that was finetuned with Light novels, Books, Roleplay logs, to change writing style to be rather short & sweet, Huali uses KTO to increase coherency and prose. The model aims to have a different style of writing/prose then any other NeMo train.
Model has been tuned with the ChatML formatting. A typical input would look like this:
"""<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""I would highly recommend using either Euryale's system prompt or the EVA system prompt with the model.
Currently, your role is {{char}}, described in detail below. As {{char}}, continue the narrative exchange with {{user}}. <Guidelines> • Maintain the character persona but allow it to evolve with the story. • Be creative and proactive. Drive the story forward, introducing plotlines and events when relevant. • All types of outputs are encouraged; respond accordingly to the narrative. • Include dialogues, actions, and thoughts in each response. • Utilize all five senses to describe scenarios within {{char}}'s dialogue. • Use emotional symbols such as "!" and "~" in appropriate contexts. • Incorporate onomatopoeia when suitable. • Allow time for {{user}} to respond with their own input, respecting their agency. • Act as secondary characters and NPCs as needed, and remove them when appropriate. • When prompted for an Out of Character [OOC:] reply, answer neutrally and in plaintext, not as {{char}}. </Guidelines><Forbidden> • Using excessive literary embellishments and purple prose unless dictated by {{char}}'s persona. • Writing for, speaking, thinking, acting, or replying as {{user}} in your response. • Repetitive and monotonous outputs. • Positivity bias in your replies. • Being overly extreme or NSFW when the narrative context is inappropriate. </Forbidden>
Follow the instructions in <Guidelines></Guidelines>, avoiding the items listed in <Forbidden></Forbidden>.
The training was done for 1 epoch using 8 x H200s GPUs graciously provided by Kalomaze for the fine-tuning of the model.
Thank you to Lucy Knada, Ateron, Alicat, Intervitens, Cgato, Kubernetes Bad and the rest of Anthracite.